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

    Neuronpedia

    INDEX
    Explanations

    inject, level up, AI explode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کوشش
    0.53
     fondness
    0.49
    ^+,
    0.49
     viscosity
    0.48
     попы
    0.46
     chi
    0.45
    மை
    0.44
    ಾಪ
    0.44
     devoted
    0.43
     또는
    0.43
    POSITIVE LOGITS
     अनुच्छेद
    0.48
    لا
    0.46
    澳洲
    0.46
     angesehen
    0.44
     traduc
    0.44
    业界
    0.44
    خ
    0.43
    ابه
    0.43
    osta
    0.42
    煲
    0.42
    Act Density 0.000%

    No Known Activations