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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _manual
    -0.07
    <Unit
    -0.06
     Shield
    -0.06
     plein
    -0.06
     Pond
    -0.06
    &t
    -0.06
     Κο
    -0.06
     kia
    -0.06
     parole
    -0.06
     swollen
    -0.06
    POSITIVE LOGITS
    Considering
    0.07
    욱
    0.07
     terör
    0.07
    (Time
    0.07
    ATHER
    0.06
    GetString
    0.06
    eding
    0.06
    :::|
    0.06
    ="./
    0.06
    GB
    0.06
    Act Density 0.000%

    No Known Activations