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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Last
    -0.07
    liches
    -0.07
    층
    -0.06
     khi
    -0.06
    IMPORT
    -0.06
    _cmds
    -0.06
    Han
    -0.06
    uffling
    -0.06
    �
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    bara
    0.07
    ($('
    0.07
     revision
    0.07
    vide
    0.07
    PHONE
    0.06
    panies
    0.06
    ney
    0.06
     podr
    0.06
    inta
    0.06
    aju
    0.06
    Act Density 0.000%

    No Known Activations