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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ","",
    -0.07
    )'),↵
    -0.06
    іть
    -0.06
     krat
    -0.06
     kot
    -0.06
     terme
    -0.06
     دوباره
    -0.06
    歡
    -0.06
     тщ
    -0.06
          ↵↵
    -0.06
    POSITIVE LOGITS
    likelihood
    0.07
    -ph
    0.07
    getti
    0.07
    ><!--
    0.07
    _Helper
    0.07
    0.07
     �
    0.06
     Allison
    0.06
    _dialog
    0.06
     meets
    0.06
    Act Density 1.998%

    No Known Activations