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

    Neuronpedia

    INDEX
    Explanations

    v

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *$
    -0.07
    ?(
    -0.07
    makt
    -0.07
     Pred
    -0.06
    ;:
    -0.06
     Welfare
    -0.06
     donc
    -0.06
    _FILTER
    -0.06
    icians
    -0.06
    _HDR
    -0.06
    POSITIVE LOGITS
    孩
    0.07
     annonce
    0.07
     evacuate
    0.07
    marshal
    0.06
    .names
    0.06
    /tasks
    0.06
     swim
    0.06
     dejtingsaj
    0.06
     liber
    0.06
    .extensions
    0.06
    Act Density 0.002%

    No Known Activations