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

    Neuronpedia

    INDEX
    Explanations

    process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hel
    -0.07
     Kid
    -0.07
    óż
    -0.07
     Wu
    -0.06
    [:-
    -0.06
     E
    -0.06
    iang
    -0.06
    upa
    -0.06
    ilet
    -0.06
     Lý
    -0.06
    POSITIVE LOGITS
     masturb
    0.07
    _READ
    0.07
     Fra
    0.07
     overlay
    0.06
     [-]:
    0.06
     massac
    0.06
    -hook
    0.06
     graves
    0.06
    abis
    0.06
    LogFile
    0.06
    Act Density 0.178%

    No Known Activations