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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WEIGHT
    -0.07
    adık
    -0.07
     Newton
    -0.07
     bò
    -0.06
     implemented
    -0.06
    すぎ
    -0.06
     Uz
    -0.06
    God
    -0.06
    som
    -0.06
     instability
    -0.06
    POSITIVE LOGITS
     В
    0.07
    agr
    0.07
     mur
    0.07
    ？↵↵
    0.07
     �
    0.06
    _about
    0.06
    “To
    0.06
     eas
    0.06
    -column
    0.06
     Thur
    0.06
    Act Density 0.199%

    No Known Activations