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

    Neuronpedia

    INDEX
    Explanations

    length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Někter
    -0.07
     cellar
    -0.07
     corruption
    -0.07
     metabolism
    -0.06
     domu
    -0.06
    afi
    -0.06
     (*((
    -0.06
     Unsure
    -0.06
    <pre
    -0.06
    ốn
    -0.06
    POSITIVE LOGITS
     �
    0.06
     projectId
    0.06
    ент
    0.06
    _GF
    0.06
     liên
    0.06
    ruby
    0.06
     �
    0.06
    grim
    0.06
     conflicting
    0.06
     uncon
    0.06
    Act Density 0.008%

    No Known Activations