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

    Neuronpedia

    INDEX
    Explanations

    speech and salutations.

    oai_token-act-pair · gemini-2.0-flash

    Dialogue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     self
    -0.48
    MTI
    -0.46
    vikle
    -0.45
     sk
    -0.44
     u
    -0.43
     cellspacing
    -0.43
    щите
    -0.42
     g
    -0.42
     esca
    -0.41
    strongly
    -0.41
    POSITIVE LOGITS
    GOTREF
    0.92
    OGND
    0.90
     itſelf
    0.88
     themſelves
    0.85
     himſelf
    0.81
     Theſe
    0.78
     leſs
    0.75
     ſtand
    0.73
    fromnode
    0.72
     myſelf
    0.72
    Act Density 0.793%

    No Known Activations