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

    Neuronpedia

    INDEX
    Explanations

    journal entry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    це
    0.40
    team
    0.39
     തീരുമാന
    0.39
     Правда
    0.39
    website
    0.37
    ركات
    0.37
    ötet
    0.37
    slots
    0.36
    tomato
    0.36
     συγκ
    0.35
    POSITIVE LOGITS
     conjure
    0.42
     İş
    0.41
     (^{
    0.39
     lũ
    0.39
     ^{\
    0.37
    ราะห์
    0.37
    >\<^
    0.37
     મહિ
    0.36
    ជូន
    0.36
    itled
    0.36
    Act Density 0.000%

    No Known Activations