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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ellaneous
    -0.07
    IRROR
    -0.07
     touring
    -0.07
     Fac
    -0.07
     Pang
    -0.07
    ്
    -0.07
     Navigator
    -0.06
    Hdr
    -0.06
    _entry
    -0.06
     Ex
    -0.06
    POSITIVE LOGITS
    CW
    0.06
    賽
    0.06
     жид
    0.06
     gaat
    0.06
    })();↵
    0.06
     usando
    0.06
     [...]↵↵
    0.06
    หว
    0.06
    075
    0.06
     extravag
    0.05
    Act Density 0.012%

    No Known Activations