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

    Neuronpedia

    INDEX
    Explanations

    chemical hazards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cells
    -0.06
    oque
    -0.06
     wię
    -0.06
    OTA
    -0.06
    서관
    -0.06
     IGNORE
    -0.06
    _phone
    -0.06
    チュ
    -0.06
    _From
    -0.06
    nist
    -0.06
    POSITIVE LOGITS
     жод
    0.06
     INF
    0.06
    .ec
    0.06
    feb
    0.06
     substit
    0.06
    !
↵
    0.06
    !,↵
    0.06
     seria
    0.06
     Ebony
    0.06
    Locked
    0.06
    Act Density 0.069%

    No Known Activations