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

    Neuronpedia

    INDEX
    Explanations

    sensory body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     usually
    0.30
     عادة
    0.30
     casually
    0.30
     meestal
    0.29
     typically
    0.28
     takiego
    0.27
    usually
    0.27
     обычно
    0.27
    玾
    0.27
     usual
    0.27
    POSITIVE LOGITS
     LEARN
    0.29
     Again
    0.27
     Listen
    0.27
    再び
    0.27
    RAM
    0.27
    LISTEN
    0.26
    さらに
    0.26
    Listen
    0.26
    Listening
    0.26
     LISTEN
    0.26
    Act Density 0.002%

    No Known Activations