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

    Neuronpedia

    INDEX
    Explanations

    Mr. followed by name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     make
    0.65
    mutable
    0.64
     generate
    0.58
     ramp
    0.55
    ০০
    0.55
     seamless
    0.54
     nuts
    0.53
     populate
    0.53
     \}
    0.52
     smart
    0.51
    POSITIVE LOGITS
    inal
    0.76
    iony
    0.70
    ira
    0.69
    .??
    0.68
    iles
    0.68
    acula
    0.68
    ជំ
    0.67
    ahid
    0.67
     Odinga
    0.66
    alee
    0.66
    Act Density 0.010%

    No Known Activations