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

    Neuronpedia

    INDEX
    Explanations

    Jack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ~=
    -0.07
     تست
    -0.07
    迩
    -0.07
    ㎡
    -0.07
    同学们
    -0.07
    חינ
    -0.07
     gim
    -0.07
     busc
    -0.07
     NSMutable
    -0.07
    旻
    -0.07
    POSITIVE LOGITS
     dumped
    0.07
     [`
    0.07
    'il
    0.06
    Kar
    0.06
     depression
    0.06
     Independent
    0.06
    읅
    0.06
    していない
    0.06
     Der
    0.06
     deduction
    0.06
    Act Density 0.010%

    No Known Activations