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

    Neuronpedia

    INDEX
    Explanations

    Emm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vaccine
    -0.08
    Inline
    -0.07
     Dil
    -0.07
    _OPERATOR
    -0.06
     military
    -0.06
    -cap
    -0.06
     heat
    -0.06
    Rec
    -0.06
     payments
    -0.06
    qa
    -0.06
    POSITIVE LOGITS
     glm
    0.07
    …)↵↵
    0.07
    ....↵↵
    0.07
     surpr
    0.07
    Steel
    0.06
     exacerb
    0.06
    ....↵
    0.06
    ctype
    0.06
    .faceVertexUvs
    0.06
    .timedelta
    0.06
    Act Density 0.022%

    No Known Activations