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

    Neuronpedia

    INDEX
    Explanations

    representations of various extremes and contrasts in emotional or figurative language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    similes using 'like'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.59
     responsabilità
    -0.56
     romántica
    -0.54
    LayoutPanel
    -0.53
    dafx
    -0.51
    Życiorys
    -0.51
     compless
    -0.50
    帖最后由
    -0.48
    pegno
    -0.48
    wnież
    -0.48
    POSITIVE LOGITS
    RTCK
    0.39
     nite
    0.38
     kne
    0.38
     Diſ
    0.37
     paral
    0.36
     препратки
    0.36
     deſt
    0.36
     Roskov
    0.36
    shutil
    0.36
    gridx
    0.36
    Act Density 0.027%

    No Known Activations