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

    Neuronpedia

    INDEX
    Explanations

    costs and prices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    representation
    -0.06
    ulan
    -0.06
    Threads
    -0.06
     mindful
    -0.06
    lán
    -0.06
    copies
    -0.06
    anh
    -0.06
     true
    -0.06
     rocky
    -0.06
    署
    -0.05
    POSITIVE LOGITS
     exited
    0.08
     عفش
    0.07
     condolences
    0.07
    啪
    0.07
    .pb
    0.06
    (Tile
    0.06
     prayed
    0.06
     hodně
    0.06
    ﾚ
    0.06
    _FOLLOW
    0.06
    Act Density 0.045%

    No Known Activations