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

    Neuronpedia

    INDEX
    Explanations

    website/app usability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incap
    -0.07
     elected
    -0.06
     Husband
    -0.06
     Terror
    -0.06
     Tecn
    -0.06
     Columbus
    -0.06
     Exhaust
    -0.06
    _control
    -0.06
     Pearl
    -0.06
     Acc
    -0.06
    POSITIVE LOGITS
     maybe
    0.07
    imir
    0.06
     Barnes
    0.06
     ditch
    0.06
    сем
    0.06
    .slice
    0.06
     audible
    0.06
    Esta
    0.06
     isEqualToString
    0.06
    _ov
    0.06
    Act Density 0.025%

    No Known Activations