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

    Neuronpedia

    INDEX
    Explanations

    sentiment towards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.83
    ，
    0.65
    食
    0.64
    scotch
    0.63
     явля
    0.60
    scopes
    0.59
    餐
    0.59
     जल
    0.58
    启动
    0.58
    ссии
    0.58
    POSITIVE LOGITS
     more
    0.75
     más
    0.72
     affectionate
    0.72
     አለበት
    0.72
     SEE
    0.70
    见的
    0.70
     اكثر
    0.69
     சின்னமாக
    0.69
    讶
    0.67
     più
    0.66
    Act Density 1.717%

    No Known Activations