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

    Neuronpedia

    INDEX
    Explanations

    availability and device status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    culoskeletal
    0.50
     rations
    0.46
    args
    0.46
     who
    0.46
    reys
    0.45
     barking
    0.45
     scales
    0.44
     피부
    0.44
     যিনি
    0.43
    ches
    0.43
    POSITIVE LOGITS
    ע
    0.54
     STREET
    0.50
     communists
    0.47
    ;
    0.47
    SAFETY
    0.46
    성은
    0.46
    কাল
    0.45
    र
    0.45
    逄
    0.45
     Canal
    0.45
    Act Density 0.001%

    No Known Activations