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

    Neuronpedia

    INDEX
    Explanations

    borderline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🇾
    -0.08
    >(),↵
    -0.08
    篪
    -0.07
    acic
    -0.07
    phony
    -0.07
     addiction
    -0.07
     חודשים
    -0.07
    Northern
    -0.07
    冔
    -0.06
    𬌗
    -0.06
    POSITIVE LOGITS
     borderline
    0.07
     brackets
    0.07
    .getResources
    0.07
     heightened
    0.07
     weighting
    0.07
     seven
    0.07
    abel
    0.07
    �
    0.07
    を変え
    0.07
    高血压
    0.07
    Act Density 0.001%

    No Known Activations