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

    Neuronpedia

    INDEX
    Explanations

    ination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tk
    -0.07
     Folk
    -0.07
     Mos
    -0.07
     view
    -0.07
    Mos
    -0.07
    ristol
    -0.06
     QPointF
    -0.06
     görmek
    -0.06
     fear
    -0.06
     Hel
    -0.06
    POSITIVE LOGITS
     combination
    0.17
     combinations
    0.13
     Combination
    0.12
     combo
    0.11
    combination
    0.10
     combos
    0.10
     Combo
    0.10
     kombin
    0.09
    Comb
    0.09
     Comb
    0.09
    Act Density 0.026%

    No Known Activations