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

    Neuronpedia

    INDEX
    Explanations

    care . obligated to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ith
    0.39
    SYN
    0.39
    ಡ್
    0.39
    手数
    0.38
     rezult
    0.38
     της
    0.37
    δα
    0.37
     etapas
    0.37
     io
    0.37
    ในการ
    0.37
    POSITIVE LOGITS
    ܤ
    0.44
     juiste
    0.44
    amini
    0.43
     करेंसी
    0.42
    ProjectGuid
    0.42
     camouflage
    0.41
     tablecloth
    0.41
    注意事项
    0.41
    妆
    0.41
    rile
    0.40
    Act Density 0.004%

    No Known Activations