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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     permissions
    -0.07
     concluding
    -0.07
    _literal
    -0.06
    вод
    -0.06
     >(
    -0.06
    .Export
    -0.06
     summarizes
    -0.06
     stupid
    -0.06
     specific
    -0.06
    因此
    -0.06
    POSITIVE LOGITS
    bies
    0.07
    '].'/
    0.06
    аними
    0.06
     Pakistani
    0.06
     mělo
    0.06
    _todo
    0.06
     neob
    0.06
    _CREAT
    0.06
     moz
    0.06
     Neh
    0.06
    Act Density 0.008%

    No Known Activations