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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inds
    -0.07
     ||
↵
    -0.07
     sep
    -0.07
     healing
    -0.06
     năm
    -0.06
    making
    -0.06
    _returns
    -0.06
     Tampa
    -0.06
    -as
    -0.06
     &[
    -0.06
    POSITIVE LOGITS
     smr
    0.06
    .mousePosition
    0.06
    ิดข
    0.06
     intellectual
    0.06
    :::/
    0.06
     див
    0.06
     digs
    0.06
    (us
    0.06
    .logic
    0.06
     кад
    0.06
    Act Density 0.012%

    No Known Activations