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

    Neuronpedia

    INDEX
    Explanations

    mutations with numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _freq
    -0.07
    -yellow
    -0.07
    umericUpDown
    -0.06
     نموده
    -0.06
     střed
    -0.06
    �
    -0.06
     وهي
    -0.06
    functional
    -0.06
    -age
    -0.06
    	Q
    -0.06
    POSITIVE LOGITS
     JAXB
    0.07
     facing
    0.07
    ?'
    0.06
    Caught
    0.06
    instanc
    0.06
    stacles
    0.06
     geld
    0.06
    .bumptech
    0.06
    openssl
    0.06
    ANTI
    0.06
    Act Density 0.003%

    No Known Activations