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

    Neuronpedia

    INDEX
    Explanations

    fertil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    狐狸
    -0.07
    ponent
    -0.07
    ケア
    -0.07
     повы
    -0.07
     intric
    -0.07
    -II
    -0.07
     oil
    -0.07
     ashes
    -0.07
    还
    -0.07
     distinctions
    -0.07
    POSITIVE LOGITS
    defer
    0.07
     cref
    0.07
     Oczywiście
    0.07
    	A
    0.07
    𝚠
    0.07
    horia
    0.07
    NotNull
    0.07
    .getClassName
    0.06
    📟
    0.06
    Edward
    0.06
    Act Density 0.002%

    No Known Activations