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

    Neuronpedia

    INDEX
    Explanations

    code loops and NLP models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    登山
    0.67
    勫
    0.65
    митри
    0.65
     Hitch
    0.63
    trap
    0.63
    产品
    0.63
    ิตร
    0.62
    ıma
    0.61
    躹
    0.61
    énez
    0.61
    POSITIVE LOGITS
     go
    1.16
     turn
    1.13
     switch
    1.08
     Switch
    1.00
     include
    0.99
     Turn
    0.99
     equipped
    0.99
     included
    0.99
     includes
    0.98
    switch
    0.96
    Act Density 0.079%

    No Known Activations