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

    Neuronpedia

    INDEX
    Explanations

    negative or critical sentiments

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

    Dashes and hyphens

    np_acts-logits-general · gemini-2.0-flash

    disambiguation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.90
    contentLoaded
    -0.84
    ostok
    -0.68
    ponses
    -0.66
    ibouti
    -0.66
     LoginComponent
    -0.66
     싶
    -0.66
     WWW
    -0.64
     المعيارى
    -0.63
     bezeichneter
    -0.63
    POSITIVE LOGITS
    ––––
    1.10
     –
    1.07
     disambiguazione
    1.00
    ––
    0.95
    awtextra
    0.93
     ujednoznacz
    0.93
    –
    0.91
    }}-\
    0.84
    ‑
    0.84
    €“
    0.84
    Act Density 0.075%

    No Known Activations