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

    Neuronpedia

    INDEX
    Explanations

    those of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veggies
    0.36
     lamin
    0.34
    很多的
    0.33
     de
    0.32
     Kiara
    0.32
    的时候
    0.32
     Selena
    0.32
     Jasmine
    0.31
     kiddos
    0.31
     Wave
    0.31
    POSITIVE LOGITS
    base
    0.36
    origin
    0.32
    Miller
    0.32
    legal
    0.32
    news
    0.30
    counter
    0.30
    business
    0.30
    federal
    0.30
    council
    0.30
    ANAL
    0.29
    Act Density 0.000%

    No Known Activations