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

    Neuronpedia

    INDEX
    Explanations

    conversational text speaking about certainty, planning, or intent.

    oai_token-act-pair · gemini-2.0-flash

    Two-character strings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    

    -0.57
     démocr
    -0.57
     courants
    -0.56
     fermés
    -0.56
    ↵↵
    -0.56
     détru
    -0.55
    ..."
    -0.55
     cérami
    -0.54
    )$\\
    -0.54
     écou
    -0.54
    POSITIVE LOGITS
    ISupport
    0.74
     +
    0.64
     dm
    0.63
     hq
    0.62
     hp
    0.61
     bg
    0.60
     bs
    0.59
     Fx
    0.59
     FF
    0.58
     hb
    0.58
    Act Density 52.238%

    No Known Activations