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

    Neuronpedia

    INDEX
    Explanations

    pension, disputes, pipeline, concerns, memory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ็ก
    0.43
    shapeColor
    0.42
    পাঁ
    0.41
     argumentation
    0.40
     простран
    0.40
     FRA
    0.39
     Giulio
    0.39
     enlightenment
    0.39
    uangan
    0.39
    ionalmente
    0.39
    POSITIVE LOGITS
    Terror
    0.36
    steal
    0.36
     key
    0.35
     samostat
    0.35
    tea
    0.34
     miles
    0.34
     bec
    0.34
    terrorism
    0.33
     Abandon
    0.33
     Guidance
    0.33
    Act Density 0.000%

    No Known Activations