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

    Neuronpedia

    INDEX
    Explanations

    Code and libraries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('#
    -0.07
    stime
    -0.07
    getResource
    -0.06
     Yours
    -0.06
    상의
    -0.06
    824
    -0.06
    ubah
    -0.06
    _targets
    -0.06
     OT
    -0.06
     installed
    -0.06
    POSITIVE LOGITS
     protesting
    0.07
    ็กซ
    0.06
     př
    0.06
    ixel
    0.06
    -bootstrap
    0.06
     unintended
    0.06
     deux
    0.06
    cstdint
    0.06
    guided
    0.06
    own
    0.06
    Act Density 0.010%

    No Known Activations