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

    Neuronpedia

    INDEX
    Explanations

    ost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PROP
    -0.07
     needy
    -0.07
    增加
    -0.07
     jade
    -0.07
     phía
    -0.07
    /editor
    -0.07
    竽
    -0.07
     sandwich
    -0.07
    _floor
    -0.06
    一句
    -0.06
    POSITIVE LOGITS
    竑
    0.08
    看重
    0.07
    تقارير
    0.06
    .GenerationType
    0.06
    ést
    0.06
    톺
    0.06
    𨭉
    0.06
    悸
    0.06
    ventus
    0.06
    (it
    0.06
    Act Density 0.005%

    No Known Activations