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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ปร
    -0.06
    sometimes
    -0.06
    Neighbors
    -0.06
    chs
    -0.06
    UITextField
    -0.06
    ****************************************************************************
    -0.06
     verificar
    -0.06
    .Are
    -0.06
    Twenty
    -0.06
    budget
    -0.06
    POSITIVE LOGITS
    nett
    0.07
    θε
    0.07
     intoxicated
    0.07
    .platform
    0.06
     β
    0.06
    -api
    0.06
     디
    0.06
    第二
    0.06
    ्शन
    0.06
    _nt
    0.06
    Act Density 0.020%

    No Known Activations