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

    Neuronpedia

    INDEX
    Explanations

    tokens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interceptor
    -0.08
    _BOOL
    -0.07
    "default
    -0.07
     DEA
    -0.07
    '].'"
    -0.07
    [text
    -0.07
    TRIES
    -0.07
     внутр
    -0.07
    χι
    -0.06
    -command
    -0.06
    POSITIVE LOGITS
    idelberg
    0.07
    ление
    0.06
     leveled
    0.06
     предостав
    0.06
     enjoyed
    0.06
    arged
    0.06
     pick
    0.06
    edish
    0.06
     cries
    0.06
    YouTube
    0.05
    Act Density 0.000%

    No Known Activations