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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ahead
    -0.06
    itan
    -0.06
    pegawai
    -0.06
     Freeman
    -0.06
     yaptır
    -0.06
    _objs
    -0.06
    _invite
    -0.06
    ेट
    -0.06
    	set
    -0.06
    	en
    -0.06
    POSITIVE LOGITS
    Tip
    0.07
     improve
    0.07
    -ag
    0.06
    нівер
    0.06
     Goblin
    0.06
     Brun
    0.06
     friendly
    0.06
    جموع
    0.06
     dağ
    0.06
    ezpe
    0.06
    Act Density 0.188%

    No Known Activations