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

    Neuronpedia

    INDEX
    Explanations

    comprehensive or detailed guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     capabilities
    0.49
    Ŝ
    0.46
    Ⲑ
    0.46
     nuclei
    0.46
     metrizable
    0.46
    ഭം
    0.46
    ณ์
    0.46
    TERN
    0.46
    метр
    0.46
     accél
    0.45
    POSITIVE LOGITS
    hope
    0.42
    be
    0.41
    burn
    0.40
    讓人
    0.39
     Cooling
    0.37
     Often
    0.37
    kaan
    0.37
     Catering
    0.36
    gung
    0.36
    coffee
    0.36
    Act Density 0.001%

    No Known Activations