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

    Neuronpedia

    INDEX
    Explanations

    Asking "how are you?"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rejection
    -0.07
     heir
    -0.06
    :",↵
    -0.06
    (report
    -0.06
    >$
    -0.06
     fantas
    -0.06
     cream
    -0.06
     nightmares
    -0.06
    rne
    -0.06
    ricao
    -0.06
    POSITIVE LOGITS
     fading
    0.07
    ,mid
    0.06
    ительность
    0.06
     навч
    0.06
    _LIMIT
    0.06
     ulong
    0.06
    ового
    0.06
     LU
    0.06
    abei
    0.06
    ฝ
    0.06
    Act Density 0.041%

    No Known Activations