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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :f
    -0.08
    inions
    -0.07
     elő
    -0.07
    agn
    -0.07
     twink
    -0.07
    ӕ
    -0.07
    稳固
    -0.07
    .lv
    -0.07
    聆
    -0.07
     affiliates
    -0.07
    POSITIVE LOGITS
     explodes
    0.07
    Writer
    0.07
     không
    0.07
    Textbox
    0.07
     extra
    0.07
     cmp
    0.07
    school
    0.06
    hospital
    0.06
     Smith
    0.06
     Freedom
    0.06
    Act Density 0.182%

    No Known Activations