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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hecho
    -0.06
     send
    -0.06
    .os
    -0.06
     คำ
    -0.06
    ़्
    -0.06
    郭
    -0.06
     verbess
    -0.06
     crime
    -0.06
     loving
    -0.06
     cruel
    -0.06
    POSITIVE LOGITS
    pollo
    0.07
    _Entity
    0.07
    -det
    0.07
    blocked
    0.06
    apiro
    0.06
    prising
    0.06
    amics
    0.06
     uninsured
    0.06
    olly
    0.06
    izontally
    0.06
    Act Density 0.000%

    No Known Activations