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

    Neuronpedia

    INDEX
    Explanations

    crisis hotlines and helplines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    platform
    0.75
    Restriction
    0.74
    Capable
    0.73
    unit
    0.72
    capable
    0.68
    nails
    0.67
     बजे
    0.66
    api
    0.65
     beatae
    0.65
    encrypted
    0.64
    POSITIVE LOGITS
     informants
    0.87
     OFF
    0.82
     डॉक्ट
    0.81
     euthanasia
    0.81
     offrir
    0.81
     wandering
    0.80
    を進
    0.80
     addTask
    0.79
     लैपटॉप
    0.79
    ieson
    0.79
    Act Density 0.114%

    No Known Activations