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

    Neuronpedia

    INDEX
    Explanations

    voting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	elif
    -0.07
     BDS
    -0.06
     harbour
    -0.06
     Lam
    -0.06
     Macro
    -0.06
    _hor
    -0.06
    Macro
    -0.06
     lda
    -0.06
    _DEFIN
    -0.06
     Weld
    -0.06
    POSITIVE LOGITS
    ają
    0.07
    immutable
    0.07
     nouvelles
    0.07
    voie
    0.06
     yasak
    0.06
    ="{
    0.06
     patient
    0.06
     alo
    0.06
     calling
    0.06
    арі
    0.06
    Act Density 0.009%

    No Known Activations