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

    Neuronpedia

    INDEX
    Explanations

    const

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assassination
    -0.08
     suicidal
    -0.07
    "F
    -0.07
     Liz
    -0.07
    SF
    -0.07
    بين
    -0.07
     sea
    -0.07
    Textarea
    -0.06
    ADF
    -0.06
    ACES
    -0.06
    POSITIVE LOGITS
    ひと
    0.06
     famille
    0.06
    decl
    0.06
    forces
    0.06
    +',
    0.06
     française
    0.06
     vulner
    0.06
    _THROW
    0.06
     склада
    0.06
    流量
    0.06
    Act Density 0.015%

    No Known Activations