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

    Neuronpedia

    INDEX
    Explanations

    lower

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิกา
    -0.07
    ��
    -0.06
    _est
    -0.06
    inos
    -0.06
     пері
    -0.06
     Clan
    -0.06
     Pikachu
    -0.06
     casino
    -0.06
    eliness
    -0.06
     نسبت
    -0.06
    POSITIVE LOGITS
     lowered
    0.13
     lowering
    0.11
     lowers
    0.08
     fucked
    0.07
     firearm
    0.07
     Cambridge
    0.07
     내려
    0.07
     Soldiers
    0.07
     Kup
    0.06
    -launch
    0.06
    Act Density 0.004%

    No Known Activations