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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical processes and mechanisms in engineering and biology

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

    loosen, soften, break, dissolve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.73
    MarshalTo
    -0.63
    aarrggbb
    -0.63
    genodigd
    -0.62
     uſe
    -0.61
     ſta
    -0.60
     Anſ
    -0.60
     Dieſe
    -0.60
     otomatig
    -0.60
     myſelf
    -0.59
    POSITIVE LOGITS
     gal
    0.36
    DataPropertyName
    0.35
     allowing
    0.33
    izr
    0.33
     unlock
    0.31
     enabling
    0.30
     Allowing
    0.30
     loosened
    0.29
     assist
    0.29
     facilitating
    0.29
    Act Density 0.059%

    No Known Activations