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

    Neuronpedia

    INDEX
    Explanations

    giving you help or advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.27
    。",
    0.22
    ；
    0.20
    ។
    0.19
    ;
    0.18
    which
    0.18
    ().
    0.18
     والذي
    0.18
    (),
    0.18
    。\
    0.18
    POSITIVE LOGITS
     advice
    0.24
     insight
    0.23
    ное
    0.23
     predic
    0.22
     guidance
    0.22
     supporto
    0.22
     support
    0.21
     insights
    0.21
     credence
    0.21
     prompt
    0.21
    Act Density 0.337%

    No Known Activations