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

    Neuronpedia

    INDEX
    Explanations

    high or low characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ১
    1.63
    ৭
    1.22
    ال
    1.13
    ৮
    1.07
    ২১
    1.07
    و
    1.05
    nesday
    1.04
    anders
    1.02
    よび
    1.00
    ровка
    1.00
    POSITIVE LOGITS
     priced
    1.65
    不高
    1.43
    1.42
    高的
    1.33
     rendah
    1.25
     Ansprüche
    1.24
     acuity
    1.24
     bidder
    1.21
    priced
    1.21
     alis
    1.20
    Act Density 0.234%

    No Known Activations