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

    Neuronpedia

    INDEX
    Explanations

    When

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    讓
    -0.07
     ».
    -0.07
    ่งข
    -0.07
    emp
    -0.07
     contingency
    -0.07
    休
    -0.06
    公路
    -0.06
    rypto
    -0.06
    .StatusInternalServerError
    -0.06
    。（
    -0.06
    POSITIVE LOGITS
    Alignment
    0.07
    ää
    0.06
    -backed
    0.06
    iostream
    0.06
     जव
    0.06
     critically
    0.06
    HashCode
    0.06
    <AudioSource
    0.06
     fully
    0.06
     Script
    0.06
    Act Density 0.030%

    No Known Activations