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

    Neuronpedia

    INDEX
    Explanations

    thinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     luder
    -0.07
    _MODULE
    -0.07
    anned
    -0.06
     Lud
    -0.06
     taped
    -0.06
     теперь
    -0.06
     Millions
    -0.06
     아니
    -0.06
     Sinai
    -0.06
    Sz
    -0.06
    POSITIVE LOGITS
     движ
    0.07
    isex
    0.07
    ()-
    0.06
    <Rigidbody
    0.06
    melon
    0.06
    _relation
    0.06
    295
    0.06
     prefixes
    0.06
     سنگ
    0.06
    @author
    0.06
    Act Density 0.000%

    No Known Activations