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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    リンク
    -0.07
     EOF
    -0.06
    .Insert
    -0.06
    phone
    -0.06
     Flower
    -0.06
     Alic
    -0.06
    erate
    -0.06
     �
    -0.06
    _BYTE
    -0.06
     Ces
    -0.06
    POSITIVE LOGITS
    OCK
    0.07
     pp
    0.07
     tournament
    0.07
    wav
    0.06
    onitor
    0.06
     granting
    0.06
    spr
    0.06
    SerializedName
    0.06
     correcting
    0.06
     NAMES
    0.06
    Act Density 0.026%

    No Known Activations