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

    Neuronpedia

    INDEX
    Explanations

    the phrase "had a" or "had this"

    oai_token-act-pair · gemini-2.0-flash

    had

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дописавши
    -0.63
     Administrativna
    -0.59
    헌
    -0.54
    guió
    -0.52
    PreferredItem
    -0.52
     FetchType
    -0.51
    enderror
    -0.50
     blew
    -0.50
    atak
    -0.48
     fece
    -0.48
    POSITIVE LOGITS
    UnsafeEnabled
    0.54
    ranton
    0.51
     voors
    0.51
    loadModel
    0.50
    ariste
    0.50
     plumes
    0.49
     comigo
    0.48
    occasion
    0.48
    abadi
    0.47
    Barre
    0.46
    Act Density 0.703%

    No Known Activations