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

    Neuronpedia

    INDEX
    Explanations

    in crisis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stö
    0.41
     비롯
    0.41
    годні
    0.41
     jä
    0.40
     Aren
    0.40
     बाजू
    0.39
     asuntos
    0.38
     côtés
    0.38
     coi
    0.38
     vista
    0.38
    POSITIVE LOGITS
     transition
    0.46
    or
    0.41
     characterized
    0.40
     which
    0.40
    which
    0.39
     restrictive
    0.38
    isce
    0.38
    program
    0.37
     crisis
    0.37
    力が
    0.36
    Act Density 0.018%

    No Known Activations