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

    Neuronpedia

    INDEX
    Explanations

    install Malware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    0.68
    es
    0.61
    с
    0.59
     de
    0.54
    -
    0.53
    ar
    0.50
    പ
    0.49
    While
    0.48
    ป
    0.47
    К
    0.47
    POSITIVE LOGITS
    lamualaikum
    0.50
    oxifen
    0.49
     sbParams
    0.49
     sportsmen
    0.47
     হাদী
    0.46
    お届け
    0.46
    思います
    0.46
    ONU
    0.46
    JSPA
    0.45
     博文
    0.45
    Act Density 0.000%

    No Known Activations