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

    Neuronpedia

    INDEX
    Explanations

    enti

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    Org
    -0.06
     retired
    -0.06
     compromised
    -0.06
     hamburg
    -0.06
     opciones
    -0.06
    /es
    -0.06
     vou
    -0.06
     \`
    -0.05
    tě
    -0.05
    POSITIVE LOGITS
     neatly
    0.16
    cplusplus
    0.14
    enti
    0.13
     Petty
    0.09
    ready
    0.08
    READY
    0.08
    '↵
    0.07
    "↵
    0.07
     distancing
    0.07
    าษฎ
    0.07
    Act Density 0.003%

    No Known Activations