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

    Neuronpedia

    INDEX
    Explanations

    say "bonus"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :{
↵
    -0.07
    sig
    -0.06
     paused
    -0.06
    subs
    -0.06
    ذكر
    -0.06
     بررسی
    -0.06
    ignum
    -0.06
    Adapter
    -0.06
     بدان
    -0.06
    [,
    -0.06
    POSITIVE LOGITS
     request
    0.07
     автор
    0.06
    <B
    0.06
    )="
    0.06
     Anonymous
    0.06
    .mk
    0.06
    ricane
    0.06
    .pk
    0.06
    }";↵
    0.06
     NGO
    0.06
    Act Density 0.069%

    No Known Activations