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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    家庭
    -0.07
    暂
    -0.07
    ỏ
    -0.06
    -forward
    -0.06
     Lebens
    -0.06
    _xs
    -0.06
     ''.
    -0.06
     сх
    -0.06
    spm
    -0.06
     OSI
    -0.06
    POSITIVE LOGITS
    @
    0.09
     architecture
    0.07
     @
    0.07
    @g
    0.07
    @m
    0.06
     Birthday
    0.06
    @n
    0.06
    Instagram
    0.06
     Rough
    0.06
    (credentials
    0.06
    Act Density 0.001%

    No Known Activations