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

    Neuronpedia

    INDEX
    Explanations

    decision-making

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     док
    -0.07
     Greg
    -0.06
    ;k
    -0.06
     Wyatt
    -0.06
     explo
    -0.06
    ยว
    -0.06
    /****************
    -0.06
     lying
    -0.06
    .cn
    -0.06
     Pam
    -0.06
    POSITIVE LOGITS
    ilarity
    0.06
    .eng
    0.06
     demolished
    0.06
    isión
    0.06
    IconButton
    0.06
    editable
    0.06
    fmt
    0.06
    _vendor
    0.06
    "struct
    0.06
    -components
    0.06
    Act Density 0.039%

    No Known Activations