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

    Neuronpedia

    INDEX
    Explanations

    smart soft easy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Palacio
    0.68
     வன
    0.66
     만
    0.65
    ount
    0.63
     urgency
    0.62
     complexity
    0.62
    шений
    0.61
    杢
    0.61
    schemas
    0.61
     bathroom
    0.60
    POSITIVE LOGITS
     Intu
    1.06
    Intu
    1.04
     Soft
    0.93
     Easy
    0.91
    Soft
    0.91
     Smart
    0.89
    Easy
    0.89
     Intelligent
    0.88
    soft
    0.87
    Smart
    0.82
    Act Density 0.128%

    No Known Activations