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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    教育
    -0.07
    欲
    -0.07
    führ
    -0.07
    unk
    -0.06
     برخورد
    -0.06
     hips
    -0.06
    /thread
    -0.06
    accine
    -0.06
     Athens
    -0.06
    doing
    -0.06
    POSITIVE LOGITS
     В
    0.06
     Brennan
    0.06
     hạt
    0.06
     dök
    0.06
    PEND
    0.05
    ταση
    0.05
    <<<<<<<<
    0.05
     kararı
    0.05
     giác
    0.05
    chal
    0.05
    Act Density 0.139%

    No Known Activations