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

    Neuronpedia

    INDEX
    Explanations

    create a date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Суриков
    0.42
     overruled
    0.38
    ieh
    0.38
    )^{*}
    0.37
     empowering
    0.36
     Stella
    0.36
    കെ
    0.36
     Specialties
    0.36
     SKIN
    0.36
     preferred
    0.35
    POSITIVE LOGITS
    Trad
    0.41
    Produce
    0.39
    Produced
    0.37
    Generated
    0.37
    咸
    0.35
     בת
    0.35
    Exclude
    0.35
    (/^\
    0.35
    ября
    0.35
    testimonials
    0.35
    Act Density 0.000%

    No Known Activations