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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    untu
    -0.08
    doctor
    -0.07
    вроп
    -0.06
     Haram
    -0.06
    .Sign
    -0.06
    DEC
    -0.06
    aters
    -0.06
     Sexo
    -0.06
     phần
    -0.06
    -0.06
    POSITIVE LOGITS
     />}
    0.06
    icester
    0.06
     содерж
    0.06
    (gulp
    0.06
    =size
    0.06
    ='')
    0.06
    izabeth
    0.06
     vont
    0.06
    _DIGEST
    0.06
    _balance
    0.06
    Act Density 0.053%

    No Known Activations