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

    Neuronpedia

    INDEX
    Explanations

    understanding human

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    أ
    0.57
    يمكن
    0.52
    Ba
    0.51
     全部
    0.51
     طريقة
    0.51
    专业
    0.50
    British
    0.50
    Travel
    0.49
    Todas
    0.48
    Dig
    0.48
    POSITIVE LOGITS
     bridge
    0.50
    IBRARY
    0.50
     fum
    0.45
     Ν
    0.44
     cadast
    0.44
     BRIDGE
    0.44
     structure
    0.43
     wound
    0.43
    sein
    0.43
     sahib
    0.42
    Act Density 0.000%

    No Known Activations