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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    파트
    -0.06
     ciphertext
    -0.06
    isd
    -0.06
     Ask
    -0.06
    .Parse
    -0.06
     solve
    -0.06
    sWith
    -0.06
    灵气
    -0.06
     comparatively
    -0.06
    креп
    -0.06
    POSITIVE LOGITS
    ária
    0.07
    疗
    0.07
     Yorkers
    0.07
    borah
    0.07
    室友
    0.07
     הישראל
    0.07
    ولات
    0.07
    استعراض
    0.06
    音乐会
    0.06
     Gäste
    0.06
    Act Density 0.001%

    No Known Activations