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

    Neuronpedia

    INDEX
    Explanations

    options, choices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     babes
    -0.08
    ᕤ
    -0.07
    鉴于
    -0.07
    凰
    -0.07
     captivating
    -0.07
     педаг
    -0.07
    𝓁
    -0.07
    גב
    -0.07
    (mContext
    -0.06
    ➰
    -0.06
    POSITIVE LOGITS
     inner
    0.07
    Shader
    0.07
     Crom
    0.06
    Close
    0.06
     Server
    0.06
     epidemic
    0.06
    	play
    0.06
     imports
    0.06
     sistemas
    0.06
    Primitive
    0.06
    Act Density 0.099%

    No Known Activations