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

    Neuronpedia

    INDEX
    Explanations

    988 Suicide & Crisis Lifeline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Srivastava
    0.38
     Okamoto
    0.38
     localhost
    0.37
    shown
    0.37
    django
    0.36
     `:
    0.36
    லைப்
    0.36
     ":
    0.35
     nonlinear
    0.35
    酭
    0.35
    POSITIVE LOGITS
     ၊
    0.55
    ULU
    0.41
    ENCIA
    0.41
    ដ្ឋ
    0.40
    apu
    0.40
    elu
    0.39
    ENTA
    0.39
    hau
    0.38
    他也
    0.37
    ves
    0.37
    Act Density 0.011%

    No Known Activations