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

    Neuronpedia

    INDEX
    Explanations

    any, every, completely, available, superior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cially
    0.79
     등을
    0.74
     leeway
    0.72
     onlookers
    0.71
     dangling
    0.70
    rä
    0.69
     lenient
    0.69
    드를
    0.69
     precarious
    0.68
     bystanders
    0.68
    POSITIVE LOGITS
     thefe
    0.85
     herhangi
    0.79
     setiap
    0.73
     minden
    0.73
     potpuno
    0.72
     memberikan
    0.68
     mevcut
    0.67
     assolutamente
    0.67
     qualsiasi
    0.67
     superiore
    0.67
    Act Density 0.000%

    No Known Activations