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

    Neuronpedia

    INDEX
    Explanations

    description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eyebrows
    -0.07
     callbacks
    -0.07
    experiment
    -0.06
     centroid
    -0.06
    cube
    -0.06
     �
    -0.06
     gpu
    -0.06
     randomNumber
    -0.06
    basePath
    -0.06
    _rb
    -0.06
    POSITIVE LOGITS
     прид
    0.07
     홍
    0.06
     fod
    0.06
    -bel
    0.06
    ký
    0.06
     Zo
    0.06
     خرد
    0.06
     buffs
    0.06
     routinely
    0.06
     Correspond
    0.06
    Act Density 0.025%

    No Known Activations