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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chili
    -0.08
     subtype
    -0.07
    尽早
    -0.07
     Prop
    -0.07
     <?=
    -0.07
    考古
    -0.07
    )'),
    -0.07
     במהלך
    -0.07
    .");↵↵
    -0.07
    />.↵
    -0.06
    POSITIVE LOGITS
    房貸
    0.08
    さて
    0.08
    -it
    0.07
     superClass
    0.07
    Margins
    0.07
    _MOV
    0.07
    蘑菇
    0.07
    开水
    0.07
     hatte
    0.07
    Meta
    0.07
    Act Density 0.002%

    No Known Activations