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

    Neuronpedia

    INDEX
    Explanations

    mmo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SHOULD
    -0.07
    มข
    -0.07
    shade
    -0.07
    ับผ
    -0.06
     unaware
    -0.06
     silence
    -0.06
     fasc
    -0.06
    ADDE
    -0.06
     Norte
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ButtonText
    0.07
    .getBoolean
    0.06
    Nut
    0.06
    .i
    0.06
    …"↵↵
    0.06
    .fragment
    0.06
     benchmark
    0.06
     روابط
    0.06
    】,
    0.06
     mixer
    0.06
    Act Density 0.000%

    No Known Activations