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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     given
    -0.06
     anger
    -0.06
    etc
    -0.06
     htons
    -0.06
     Repair
    -0.06
     변
    -0.06
    _ar
    -0.06
     Islam
    -0.06
    ］
    -0.06
    POSITIVE LOGITS
    има
    0.07
     Cristiano
    0.07
     těž
    0.07
    asaki
    0.07
     letra
    0.06
    Cool
    0.06
    니다
    0.06
    ğinden
    0.06
     CRC
    0.06
    бира
    0.06
    Act Density 0.009%

    No Known Activations