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

    Neuronpedia

    INDEX
    Explanations

    materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Adj
    -0.07
    ίο
    -0.07
    precision
    -0.07
    _CERT
    -0.06
     bite
    -0.06
     Toe
    -0.06
    checksum
    -0.06
     Dexter
    -0.06
    нию
    -0.06
    _j
    -0.06
    POSITIVE LOGITS
    ducted
    0.07
    選
    0.07
     hombres
    0.06
    imentary
    0.06
     tendencies
    0.06
     Ethan
    0.06
     Whole
    0.06
     grayscale
    0.06
    ených
    0.06
    solid
    0.06
    Act Density 0.000%

    No Known Activations