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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Made
    -0.08
     gouver
    -0.08
     Liber
    -0.07
    olve
    -0.07
    .expand
    -0.06
     และ
    -0.06
    .vector
    -0.06
     kidnapped
    -0.06
     recorded
    -0.06
     Torch
    -0.06
    POSITIVE LOGITS
    sq
    0.07
    alsex
    0.06
    (Constants
    0.06
     anonymity
    0.06
    いつ
    0.06
    τρ
    0.06
    し
    0.06
     عقد
    0.06
     villains
    0.06
    さんは
    0.06
    Act Density 0.001%

    No Known Activations