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

    Neuronpedia

    INDEX
    Explanations

    barrier to entry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ភេទ
    0.49
    quete
    0.48
    传输
    0.45
     consideran
    0.45
    addKill
    0.44
    multiSelectList
    0.44
    匀
    0.44
     தரும்
    0.44
    ᱕
    0.44
    ahooks
    0.44
    POSITIVE LOGITS
     accumulation
    0.49
     Tomato
    0.44
    િ
    0.43
     Creation
    0.41
     Inspirational
    0.40
     Unicode
    0.39
     ū
    0.39
    قد
    0.39
     creation
    0.38
     rundt
    0.38
    Act Density 0.003%

    No Known Activations