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

    Neuronpedia

    INDEX
    Explanations

    consent and coal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surpass
    0.43
     оконча
    0.39
     surpassing
    0.39
    得上
    0.39
    䒺
    0.38
    ெற்ற
    0.37
     solv
    0.37
    ргә
    0.37
    劣
    0.37
    鼕
    0.37
    POSITIVE LOGITS
     Cast
    0.45
     Andersen
    0.39
     этими
    0.39
    adeh
    0.39
     water
    0.38
    ífer
    0.38
    anta
    0.38
     Practices
    0.38
    aze
    0.38
     Water
    0.37
    Act Density 0.000%

    No Known Activations