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

    Neuronpedia

    INDEX
    Explanations

    backtick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —and
    -0.07
     fallout
    -0.06
    into
    -0.06
     theres
    -0.06
    Bubble
    -0.06
     Diego
    -0.06
     attractiveness
    -0.06
     dagen
    -0.06
     outings
    -0.06
     ella
    -0.06
    POSITIVE LOGITS
    SJ
    0.07
    _tac
    0.07
    ρ
    0.06
     port
    0.06
     ct
    0.06
    ζ
    0.06
    ीआई
    0.06
    .accessToken
    0.06
     Port
    0.06
     hostage
    0.06
    Act Density 0.019%

    No Known Activations