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

    Neuronpedia

    INDEX
    Explanations

    collision avoidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    applicazione
    0.75
    I
    0.73
    াউন্ড
    0.71
     sottop
    0.71
    எஸ்
    0.69
    Q
    0.69
    vol
    0.68
    ripción
    0.68
    rizione
    0.68
    DEN
    0.67
    POSITIVE LOGITS
     intestines
    0.87
     carriages
    0.85
     concurrency
    0.84
     cottages
    0.82
     vasodil
    0.82
     kayaks
    0.80
     militias
    0.79
     carcasses
    0.79
     Rupees
    0.78
     canoes
    0.78
    Act Density 0.001%

    No Known Activations