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

    Neuronpedia

    INDEX
    Explanations

    p

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мас
    -0.06
     Ю
    -0.06
     disagreement
    -0.06
    >D
    -0.06
    spaces
    -0.06
    _phys
    -0.06
    /Form
    -0.06
     sess
    -0.06
     angered
    -0.06
    isbury
    -0.06
    POSITIVE LOGITS
     legit
    0.07
    _DELETE
    0.06
    χν
    0.06
    すす
    0.06
     InternalEnumerator
    0.06
    <Service
    0.06
     FieldType
    0.06
     Repeat
    0.06
    _Run
    0.06
    -east
    0.06
    Act Density 0.008%

    No Known Activations