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

    Neuronpedia

    INDEX
    Explanations

    ag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ову
    -0.07
    وره
    -0.06
    immer
    -0.06
    grily
    -0.06
     Gov
    -0.06
     mirrors
    -0.06
     xxxx
    -0.06
     دادن
    -0.06
    овах
    -0.06
    arrays
    -0.06
    POSITIVE LOGITS
     overcome
    0.07
     telefon
    0.07
     aplik
    0.07
     bağ
    0.07
    /;↵
    0.07
     philosoph
    0.06
    演
    0.06
     поэтому
    0.06
     unfortunately
    0.06
     sodom
    0.06
    Act Density 0.507%

    No Known Activations