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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    authority
    -0.07
    ょう
    -0.07
    zero
    -0.07
    _switch
    -0.07
    _LOGGER
    -0.07
    nP
    -0.06
    анню
    -0.06
    rip
    -0.06
    (movie
    -0.06
     Thumbnails
    -0.06
    POSITIVE LOGITS
     개인
    0.07
     подс
    0.07
    	GLuint
    0.06
     Activ
    0.06
     Applying
    0.06
    (bc
    0.06
    (des
    0.06
    .В
    0.06
     kys
    0.06
    (sv
    0.06
    Act Density 0.008%

    No Known Activations