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

    Neuronpedia

    INDEX
    Explanations

    built

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    _RM
    -0.07
     MC
    -0.06
    กรม
    -0.06
     knocking
    -0.06
    iele
    -0.06
    PP
    -0.06
    hee
    -0.06
     WW
    -0.06
     Clips
    -0.06
    POSITIVE LOGITS
     fluct
    0.07
     си
    0.07
     rejo
    0.06
     никогда
    0.06
    .voice
    0.06
    	wait
    0.06
     定
    0.06
    ()");↵
    0.06
    DISABLE
    0.06
    İTESİ
    0.06
    Act Density 0.134%

    No Known Activations