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

    Neuronpedia

    INDEX
    Explanations

    manual processes and triggers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    otlin
    -0.08
    egna
    -0.08
    ři
    -0.07
     Ravi
    -0.07
    traits
    -0.07
    rola
    -0.07
     Valentin
    -0.07
    Combine
    -0.07
     ром
    -0.07
     Romano
    -0.07
    POSITIVE LOGITS
     manual
    0.16
     manually
    0.15
    .manual
    0.15
    manual
    0.14
    Manual
    0.14
     Manual
    0.14
    _manual
    0.14
     manuel
    0.13
     вруч
    0.13
     intentionally
    0.12
    Act Density 0.049%

    No Known Activations