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

    Neuronpedia

    INDEX
    Explanations

    p

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     losers
    -0.07
     جلسه
    -0.07
    .desc
    -0.07
     histo
    -0.07
     chiff
    -0.07
     کام
    -0.06
    ournée
    -0.06
     vendors
    -0.06
     GOODMAN
    -0.06
     "==
    -0.06
    POSITIVE LOGITS
    p
    0.09
    py
    0.07
    PK
    0.07
    ph
    0.07
    PS
    0.06
    Use
    0.06
     Philipp
    0.06
     Strawberry
    0.06
    ↓
    0.06
    ps
    0.06
    Act Density 0.001%

    No Known Activations