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

    Neuronpedia

    INDEX
    Explanations

    introducing yourself or others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Parad
    0.37
     وفا
    0.36
     mwaka
    0.36
    Cairo
    0.35
     Charleston
    0.35
    岁的
    0.35
     Aub
    0.34
     Cairo
    0.34
    ైనా
    0.34
     Gä
    0.33
    POSITIVE LOGITS
     výstav
    0.44
    😆
    0.42
    Readable
    0.40
    Auto
    0.40
    RS
    0.40
    igg
    0.39
     doulou
    0.39
    Energy
    0.39
    북도
    0.39
    Pain
    0.39
    Act Density 0.001%

    No Known Activations