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

    Neuronpedia

    INDEX
    Explanations

    sex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    childs
    -0.07
     Vz
    -0.07
    ociety
    -0.07
    .Note
    -0.06
     Zhou
    -0.06
    TargetException
    -0.06
     Ле
    -0.06
    anlar
    -0.06
     lingering
    -0.06
    	boolean
    -0.06
    POSITIVE LOGITS
    SON
    0.06
     suck
    0.06
     rifles
    0.06
    емого
    0.06
    �
    0.06
    ап
    0.06
    ',{↵
    0.06
     �
    0.06
     prejudices
    0.06
    ''
    0.06
    Act Density 0.006%

    No Known Activations