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

    Neuronpedia

    INDEX
    Explanations

    crisis hotlines and suicide prevention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᗰ
    0.59
     непотпу
    0.55
    ulkar
    0.53
    তন্ত্র
    0.52
     organisations
    0.52
     przedstaw
    0.52
    orphism
    0.51
     udd
    0.51
    ulint
    0.51
     prosec
    0.50
    POSITIVE LOGITS
     anytime
    1.11
     suicidal
    1.08
     Anytime
    0.93
     Suicide
    0.90
     আত্মহত্যা
    0.87
     suicide
    0.86
    随时
    0.82
     anonymously
    0.76
     jederzeit
    0.76
     nationwide
    0.75
    Act Density 0.187%

    No Known Activations