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

    Neuronpedia

    INDEX
    Explanations

    mg/kg dosage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Orwell
    0.80
    "$
    0.78
     fussy
    0.74
     nutzt
    0.71
     genutzt
    0.71
    ต่างๆ
    0.70
    jén
    0.70
    analy
    0.70
     Islands
    0.69
     namanya
    0.68
    POSITIVE LOGITS
     का
    0.91
    以上
    0.89
    。
    0.86
     के
    0.84
    イ
    0.80
    Tela
    0.78
     مركز
    0.77
    ।
    0.74
    Correction
    0.74
     श्रद्धाल
    0.74
    Act Density 0.441%

    No Known Activations