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

    Neuronpedia

    INDEX
    Explanations

    other, specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anticipated
    0.48
     plated
    0.48
    able
    0.47
    ær
    0.44
    aka
    0.44
     allowing
    0.44
    were
    0.44
    ancial
    0.44
    ley
    0.43
    allow
    0.43
    POSITIVE LOGITS
     insegn
    0.48
     Elektrokhimiya
    0.46
     poesia
    0.43
     medit
    0.43
     lentement
    0.43
     fortiter
    0.43
     poesía
    0.42
     ayahuasca
    0.42
     trabajos
    0.42
     beginnetje
    0.42
    Act Density 0.032%

    No Known Activations