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

    Neuronpedia

    INDEX
    Explanations

    Pacific

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    our
    -0.08
     SHE
    -0.08
     en
    -0.07
    _Email
    -0.07
     Rew
    -0.07
     emojis
    -0.07
     Kop
    -0.07
     grow
    -0.06
     engr
    -0.06
     Elo
    -0.06
    POSITIVE LOGITS
     Pacific
    0.16
    Pacific
    0.13
     Atlantic
    0.10
    -Pacific
    0.10
     Pac
    0.09
    bac
    0.08
    acific
    0.08
     Caf
    0.07
     AC
    0.07
    ak
    0.07
    Act Density 0.005%

    No Known Activations