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

    Neuronpedia

    INDEX
    Explanations

    US states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    投放
    -0.07
    辟
    -0.07
    _iterations
    -0.07
     halo
    -0.07
    淡
    -0.06
    Interview
    -0.06
    _Params
    -0.06
    Tur
    -0.06
     Hond
    -0.06
    	NULL
    -0.06
    POSITIVE LOGITS
    的价值
    0.07
    ihat
    0.07
    arrass
    0.07
    ילד
    0.07
    ơ
    0.07
     Biology
    0.07
    эт
    0.07
     psychological
    0.07
    conomic
    0.07
    borg
    0.06
    Act Density 0.017%

    No Known Activations