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

    Neuronpedia

    INDEX
    Explanations

    tool

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’y
    -0.07
     academics
    -0.07
     isolation
    -0.07
    铱
    -0.07
     où
    -0.07
    Know
    -0.07
     Adoption
    -0.07
     Fail
    -0.07
    えば
    -0.07
    Priority
    -0.07
    POSITIVE LOGITS
    롞
    0.08
    小姐姐
    0.07
    领会
    0.07
    숨
    0.07
    AllWindows
    0.07
    岚
    0.07
    흣
    0.07
    OLDER
    0.07
    Lookup
    0.07
    olang
    0.07
    Act Density 0.052%

    No Known Activations