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

    Neuronpedia

    INDEX
    Explanations

    insurance coverage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sampled
    -0.07
    نسية
    -0.07
    _strings
    -0.07
     Interior
    -0.07
     Integrity
    -0.07
     steril
    -0.06
    ”),
    -0.06
     disclosure
    -0.06
     device
    -0.06
    .fromString
    -0.06
    POSITIVE LOGITS
    िर
    0.07
    \Abstract
    0.06
    .her
    0.06
    -ok
    0.06
     NHL
    0.06
    -navbar
    0.06
    converted
    0.06
     �
    0.06
     btnSave
    0.06
     chill
    0.06
    Act Density 0.021%

    No Known Activations