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

    Neuronpedia

    INDEX
    Explanations

    developer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Odds
    -0.09
    Observed
    -0.09
    Duration
    -0.09
    Telephone
    -0.09
    Combat
    -0.08
    Recorded
    -0.08
    Encrypted
    -0.08
    Edited
    -0.08
    Teleport
    -0.08
    Correction
    -0.08
    POSITIVE LOGITS
    )>>
    0.08
     oferece
    0.08
     interested
    0.08
     interessados
    0.08
     ava
    0.08
     sandbox
    0.08
    指南
    0.08
     бумаги
    0.08
     anybody
    0.08
     menyediakan
    0.07
    Act Density 0.006%

    No Known Activations