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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -best
    -0.06
     Reb
    -0.06
    -issue
    -0.06
    (require
    -0.06
     disgr
    -0.06
    ohana
    -0.06
    غة
    -0.06
    ิถ
    -0.06
    अ
    -0.06
    algorithm
    -0.05
    POSITIVE LOGITS
     frames
    0.07
     signaling
    0.07
     této
    0.07
     bulun
    0.07
    birds
    0.07
     Atmos
    0.06
    edik
    0.06
     Shore
    0.06
    -hover
    0.06
    uten
    0.06
    Act Density 0.003%

    No Known Activations