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

    Neuronpedia

    INDEX
    Explanations

    H

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᘑ
    -0.07
    أطفال
    -0.07
    杨
    -0.07
    🆂
    -0.06
    פעל
    -0.06
    mutable
    -0.06
    'L
    -0.06
    حدود
    -0.06
    .SQL
    -0.06
     מהמע
    -0.06
    POSITIVE LOGITS
    ↾
    0.08
    )][
    0.07
     kitty
    0.07
    ?):
    0.07
    chos
    0.06
    Trans
    0.06
    Completion
    0.06
     forums
    0.06
     Jag
    0.06
     reaches
    0.06
    Act Density 0.017%

    No Known Activations