Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    locations and conditions suitable for storage and growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Location/storage recommendations or requirements

    np_acts-logits-general · gemini-2.0-flash

    away in a corner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pardo
    -0.52
    InstanceOf
    -0.51
    pondi
    -0.50
    isDebugEnabled
    -0.48
     Autorizaciones
    -0.44
     noDo
    -0.43
    argout
    -0.43
    +#+
    -0.42
    <bos>
    -0.42
    #+#
    -0.42
    POSITIVE LOGITS
     sheltered
    1.16
     away
    1.04
     inaccessible
    1.00
     protected
    1.00
     shielded
    0.96
    Away
    0.93
     secluded
    0.92
    away
    0.90
     Away
    0.86
     tucked
    0.86
    Act Density 0.222%

    No Known Activations