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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carga
    -0.07
     BaseModel
    -0.06
    NA
    -0.06
    idades
    -0.06
     Farms
    -0.06
     theirs
    -0.06
    TECTION
    -0.06
     швид
    -0.06
     introdu
    -0.06
    bt
    -0.06
    POSITIVE LOGITS
     เบ
    0.07
    ->{_
    0.06
     iterator
    0.06
     asshole
    0.06
     Berg
    0.06
     \\
    0.06
    _WALL
    0.06
    _SUBJECT
    0.06
     PRIMARY
    0.06
    NSUInteger
    0.06
    Act Density 0.031%

    No Known Activations