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

    Neuronpedia

    INDEX
    Explanations

    positive reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    秋
    -0.07
     cynical
    -0.06
    umed
    -0.06
    am
    -0.06
     doubt
    -0.06
     reluctantly
    -0.06
    imator
    -0.06
    ible
    -0.06
     deney
    -0.06
     reject
    -0.05
    POSITIVE LOGITS
     getEmail
    0.07
     persistence
    0.07
    -abs
    0.06
     zahrani
    0.06
     StartCoroutine
    0.06
     BASE
    0.06
     JNICALL
    0.06
     CFG
    0.06
    Matching
    0.06
     adını
    0.06
    Act Density 0.049%

    No Known Activations