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

    Neuronpedia

    INDEX
    Explanations

    scientific names or labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MPa
    0.88
    鱒
    0.87
    aterial
    0.86
    lbrakk
    0.86
    diameter
    0.86
     забезпе
    0.85
     диамет
    0.85
    entieth
    0.85
     birinci
    0.84
     মৌলিক
    0.83
    POSITIVE LOGITS
     Live
    0.76
     crying
    0.75
    Live
    0.72
     live
    0.71
     नारे
    0.69
     dwell
    0.68
     unison
    0.67
     click
    0.65
     melod
    0.64
     nerves
    0.63
    Act Density 0.002%

    No Known Activations