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

    Neuronpedia

    INDEX
    Explanations

    ---

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Emirates
    -0.06
     Fever
    -0.06
    ひと
    -0.06
     желез
    -0.06
    adress
    -0.06
     OSS
    -0.06
     جمعیت
    -0.06
     fever
    -0.06
    चन
    -0.06
    ngthen
    -0.06
    POSITIVE LOGITS
    ours
    0.07
     ARGS
    0.06
     Webb
    0.06
     RC
    0.06
    .Native
    0.06
     sacrificing
    0.06
    (EC
    0.06
    194
    0.06
    .beta
    0.06
     mounted
    0.06
    Act Density 0.002%

    No Known Activations