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

    Neuronpedia

    INDEX
    Explanations

    numerical measurements or ratios

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tarn
    -0.07
    (userInfo
    -0.06
     meer
    -0.06
    tpl
    -0.06
    ambre
    -0.06
    ама
    -0.06
     zn
    -0.06
    beer
    -0.06
    .pref
    -0.06
    remote
    -0.06
    POSITIVE LOGITS
    gression
    0.06
    rrha
    0.06
     하지
    0.06
    ordinated
    0.06
    俺
    0.06
    (Language
    0.06
    肃
    0.05
    InProgress
    0.05
    ceptive
    0.05
     booty
    0.05
    Act Density 0.076%

    No Known Activations