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

    Neuronpedia

    INDEX
    Explanations

    pathology/medical conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interpreting
    -1.16
     interpretation
    -1.06
    interpret
    -1.05
    Interpret
    -1.04
     interpret
    -0.96
     Interpret
    -0.95
     interpretations
    -0.93
     interpr
    -0.92
     INTERPRET
    -0.90
    interpretation
    -0.90
    POSITIVE LOGITS
    t
    0.63
    i
    0.51
    tan
    0.50
    te
    0.50
     IS
    0.49
    ']?>
    0.47
     em
    0.47
    '];?>
    0.46
    tres
    0.45
    sonaro
    0.45
    Act Density 0.051%

    No Known Activations