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

    Neuronpedia

    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maple
    -0.06
     E
    -0.06
     JT
    -0.06
    _ENTITY
    -0.06
     ineligible
    -0.06
     Legends
    -0.06
    .spatial
    -0.06
     <!--
    -0.05
    від
    -0.05
    Permissions
    -0.05
    POSITIVE LOGITS
     good
    0.14
    good
    0.12
     Good
    0.10
    _good
    0.10
     GOOD
    0.10
    Good
    0.09
    _GOOD
    0.08
    .good
    0.08
    -good
    0.08
    GOOD
    0.08
    Act Density 0.035%

    No Known Activations