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

    Neuronpedia

    INDEX
    Explanations

    en

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ména
    -0.07
     disreg
    -0.07
     lucrative
    -0.07
     nur
    -0.07
    ọt
    -0.06
     зада
    -0.06
    -sk
    -0.06
     agreeing
    -0.06
     remainder
    -0.06
     <<=
    -0.06
    POSITIVE LOGITS
    RIEND
    0.08
    评
    0.06
    _pipeline
    0.06
    イル
    0.06
     Mercury
    0.06
    _family
    0.06
    关系
    0.06
    ...");
↵
    0.06
    .poll
    0.06
    moon
    0.06
    Act Density 0.249%

    No Known Activations