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

    Neuronpedia

    INDEX
    Explanations

    bound

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ازم
    -0.07
    -Co
    -0.06
     Cop
    -0.06
     GP
    -0.06
    -м
    -0.06
     studio
    -0.06
    combat
    -0.06
     Ivan
    -0.06
    _'
    -0.06
    ivan
    -0.06
    POSITIVE LOGITS
    854
    0.07
     πραγμα
    0.07
    �
    0.07
     courses
    0.07
    PreferredGap
    0.06
     noticing
    0.06
    BindView
    0.06
     toen
    0.06
     alleges
    0.06
    .choose
    0.06
    Act Density 0.017%

    No Known Activations