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

    Neuronpedia

    INDEX
    Explanations

    Black community

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Update
    -0.07
    .—
    -0.07
    columns
    -0.06
     холодиль
    -0.06
     ساز
    -0.06
    Greek
    -0.06
     dvd
    -0.06
     ops
    -0.06
     DVD
    -0.06
     daß
    -0.06
    POSITIVE LOGITS
     proficiency
    0.07
     monkey
    0.06
    mnop
    0.06
    plitude
    0.06
     overl
    0.06
    :numel
    0.06
     Ej
    0.06
    ={!
    0.06
    *>(&
    0.06
    .Ma
    0.05
    Act Density 0.119%

    No Known Activations