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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cert
    -0.06
    ch
    -0.06
     알
    -0.06
     tet
    -0.06
    ENU
    -0.06
     acest
    -0.06
    Sm
    -0.06
     suspected
    -0.06
    cup
    -0.06
    noop
    -0.06
    POSITIVE LOGITS
     """.
    0.07
     Guang
    0.07
    ================
    0.07
    onec
    0.06
    andes
    0.06
    낸
    0.06
    ρη
    0.06
     Connectivity
    0.06
     impulses
    0.06
    _MONTH
    0.06
    Act Density 0.000%

    No Known Activations