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

    Neuronpedia

    INDEX
    Explanations

    single digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pager
    -0.07
     minds
    -0.07
    .Il
    -0.07
     trouble
    -0.07
    चन
    -0.07
    _tran
    -0.06
     پست
    -0.06
     Kings
    -0.06
     refuse
    -0.06
    strcasecmp
    -0.06
    POSITIVE LOGITS
     inscription
    0.07
    ovány
    0.07
    園
    0.06
    ös
    0.06
     Medal
    0.06
    agr
    0.06
     різ
    0.06
     isOpen
    0.06
    รง
    0.06
     들어
    0.06
    Act Density 0.053%

    No Known Activations