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

    Neuronpedia

    INDEX
    Explanations

    -list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FI
    -0.07
     Rounds
    -0.07
    Jones
    -0.07
    ่าท
    -0.06
     FIRST
    -0.06
     converting
    -0.06
    ong
    -0.06
     Sun
    -0.06
    .Convert
    -0.06
    周
    -0.06
    POSITIVE LOGITS
    vatel
    0.07
     tolik
    0.07
     ty
    0.07
     �
    0.06
    approximately
    0.06
    /owl
    0.06
    -grey
    0.06
     LinearGradient
    0.06
    realloc
    0.06
     dó
    0.06
    Act Density 0.015%

    No Known Activations