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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pronto
    -0.07
     destroyer
    -0.07
     occurrence
    -0.07
     subjected
    -0.07
    rice
    -0.07
    _peer
    -0.07
     mari
    -0.07
     Đ
    -0.07
    רא
    -0.07
     profiling
    -0.07
    POSITIVE LOGITS
     rumpe
    0.07
    rink
    0.07
    bedtls
    0.07
    ⚲
    0.07
    底蕴
    0.07
     flexGrow
    0.07
     withdrew
    0.07
     BaseController
    0.07
     гар
    0.06
     móg
    0.06
    Act Density 0.057%

    No Known Activations