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

    Neuronpedia

    INDEX
    Explanations

    words related to the conjunction and preposition "to"

    oai_token-act-pair · gemini-2.0-flash

    and, comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.71
     raiſ
    -0.69
     africaine
    -0.63
     setti
    -0.58
     poffe
    -0.57
     zijne
    -0.57
     pleaf
    -0.55
     bathing
    -0.55
     exceptionnelle
    -0.55
    )))),
    -0.53
    POSITIVE LOGITS
     edit
    1.05
     build
    0.99
     install
    0.98
     sell
    0.98
     fill
    0.96
     move
    0.96
     bake
    0.96
     isolate
    0.96
     kill
    0.96
     eat
    0.95
    Act Density 7.320%

    No Known Activations