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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appealed
    -0.07
     porter
    -0.07
     guarantee
    -0.06
    caller
    -0.06
    atinum
    -0.06
    Disp
    -0.06
    植
    -0.06
     supplemental
    -0.06
     Peach
    -0.06
    اور
    -0.06
    POSITIVE LOGITS
    ernals
    0.06
    .roles
    0.06
     kayı
    0.06
    Steel
    0.06
     Tempo
    0.06
     Rab
    0.06
    +"'
    0.06
    0
    0.06
    Teams
    0.06
     함수
    0.05
    Act Density 0.015%

    No Known Activations