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

    Neuronpedia

    INDEX
    Explanations

    image width in figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ravel
    0.38
     trabal
    0.34
     blant
    0.34
     peritone
    0.34
     اتصال
    0.34
     ironing
    0.34
    ्युनिकेशन
    0.33
    尃
    0.32
     metering
    0.32
    стром
    0.32
    POSITIVE LOGITS
    tikz
    0.47
    十二
    0.44
     ১১
    0.44
    req
    0.42
     proofs
    0.41
    args
    0.41
    tw
    0.40
     ১২
    0.40
    AMA
    0.39
     १२
    0.39
    Act Density 0.000%

    No Known Activations