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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _diag
    -0.07
    oundary
    -0.07
    ″N
    -0.07
    .ManyToManyField
    -0.07
    aits
    -0.06
    SSF
    -0.06
     дальней
    -0.06
     minValue
    -0.06
     compelled
    -0.06
    Statements
    -0.06
    POSITIVE LOGITS
     lamb
    0.07
     Throw
    0.06
    )[:
    0.06
     Cry
    0.06
     annoyance
    0.06
     Clothing
    0.06
    ву
    0.06
    WITH
    0.06
     Horse
    0.06
     보여
    0.06
    Act Density 0.008%

    No Known Activations