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

    Neuronpedia

    INDEX
    Explanations

    show

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oted
    -0.07
     cake
    -0.07
     atención
    -0.07
    FromBody
    -0.07
    PRINT
    -0.07
    textField
    -0.06
    REMOTE
    -0.06
    /master
    -0.06
     děti
    -0.06
     textField
    -0.06
    POSITIVE LOGITS
     nonce
    0.07
     }}">
    0.06
     SV
    0.06
     كر
    0.06
     σ
    0.06
     ii
    0.06
     qa
    0.06
     Delhi
    0.06
    akit
    0.06
     ):↵
    0.06
    Act Density 0.029%

    No Known Activations