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

    Neuronpedia

    INDEX
    Explanations

    proactive defense changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     파일을
    0.44
     Vương
    0.39
    henden
    0.38
    ফতরের
    0.38
    щает
    0.38
     Filosof
    0.38
    ⃖
    0.38
     हत्याकांड
    0.37
    COMANDA
    0.37
     Src
    0.36
    POSITIVE LOGITS
    곶
    0.42
     inland
    0.40
    ვნ
    0.39
     inlets
    0.38
     собственно
    0.38
     bram
    0.36
    זרה
    0.36
     stratum
    0.36
     अमेर
    0.36
     impulses
    0.36
    Act Density 0.000%

    No Known Activations