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

    Neuronpedia

    INDEX
    Explanations

    date suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.70
    с
    0.55
    5
    0.54
    ら
    0.52
    ge
    0.51
    4
    0.51
    Statement
    0.50
    近
    0.50
    은
    0.48
    sc
    0.48
    POSITIVE LOGITS
     oxalate
    0.65
     cyclohexane
    0.59
    iums
    0.57
     sulfon
    0.56
     விழுப்பு
    0.55
     chutney
    0.55
     cyclohex
    0.54
     choline
    0.53
     cathode
    0.50
    ﺏ
    0.50
    Act Density 0.000%

    No Known Activations