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

    Neuronpedia

    INDEX
    Explanations

    conditionals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     поверх
    -0.07
    ßen
    -0.07
     mph
    -0.07
    山坡
    -0.07
    もらう
    -0.07
     negotiate
    -0.06
    特产
    -0.06
    贫困户
    -0.06
    מסמכי
    -0.06
     האח
    -0.06
    POSITIVE LOGITS
    Յ
    0.07
     dive
    0.07
    >]
    0.07
     \'
    0.07
     hẳn
    0.07
    addOn
    0.07
    必不可
    0.07
    _ylim
    0.06
    颟
    0.06
    〝
    0.06
    Act Density 0.072%

    No Known Activations