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

    Neuronpedia

    INDEX
    Explanations

    /init

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ONLY
    -0.08
     Pearce
    -0.08
    TriState
    -0.08
    不管是
    -0.08
    大概
    -0.07
    _kind
    -0.07
    ucion
    -0.07
    思う
    -0.07
    ispens
    -0.07
    座谈
    -0.07
    POSITIVE LOGITS
     confronted
    0.08
     Warning
    0.07
     Walnut
    0.07
     flutter
    0.06
    LEAN
    0.06
    objective
    0.06
     Harold
    0.06
    ()));
↵
    0.06
    [e
    0.06
    >{
    0.06
    Act Density 0.004%

    No Known Activations