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

    Neuronpedia

    INDEX
    Explanations

    locations near or around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உலகில்
    0.46
     мире
    0.46
     ו
    0.42
    icleta
    0.42
     လ
    0.42
     யான
    0.40
     งาน
    0.40
     repress
    0.40
    ml
    0.38
    ancing
    0.38
    POSITIVE LOGITS
    رت
    0.48
     최대
    0.42
    сква
    0.41
     ezért
    0.41
     ilma
    0.39
    یک
    0.39
    upné
    0.39
    ਗਾ
    0.38
     ecuación
    0.38
     därför
    0.38
    Act Density 0.000%

    No Known Activations