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

    Neuronpedia

    INDEX
    Explanations

    note

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    centre
    -0.06
     feared
    -0.06
     mating
    -0.06
     Defendants
    -0.06
    CEL
    -0.06
    珍
    -0.06
     Rigidbody
    -0.06
    god
    -0.06
    頂
    -0.06
    mega
    -0.06
    POSITIVE LOGITS
     note
    0.11
     notes
    0.09
     Notes
    0.09
     Note
    0.08
    Notes
    0.07
    Inset
    0.07
    UNE
    0.07
     Jerome
    0.07
     psi
    0.07
    Note
    0.07
    Act Density 0.011%

    No Known Activations