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

    Neuronpedia

    INDEX
    Explanations

    based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    0.53
     prophylaxis
    0.48
     sediments
    0.47
     prophylactic
    0.45
     hath
    0.45
    ה
    0.45
     imprim
    0.44
     circumferential
    0.44
     prophyl
    0.44
    ئ
    0.44
    POSITIVE LOGITS
     இறுதியில்
    0.52
    anso
    0.48
     கிஷோர்
    0.48
    robespierre
    0.47
    minValue
    0.47
    amento
    0.46
    મેન્ટ
    0.46
    becca
    0.46
    ینڈ
    0.46
    getBlueTeam
    0.46
    Act Density 0.040%

    No Known Activations