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

    Neuronpedia

    INDEX
    Explanations

    goog

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Slave
    -0.07
     });
↵
    -0.07
     움직
    -0.07
     omas
    -0.07
     skeptic
    -0.07
     Rican
    -0.06
     yüzde
    -0.06
     вст
    -0.06
     Sorting
    -0.06
     poner
    -0.06
    POSITIVE LOGITS
    G
    0.08
    -G
    0.07
     experimented
    0.07
    üsseldorf
    0.06
    .G
    0.06
    (core
    0.06
    _constants
    0.06
     quelques
    0.06
    OG
    0.06
    غاز
    0.06
    Act Density 0.001%

    No Known Activations