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

    Neuronpedia

    INDEX
    Explanations

    Vital signs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sometimes
    -0.07
     VIR
    -0.07
    習
    -0.07
     Lopez
    -0.06
     Edge
    -0.06
     неск
    -0.06
    альне
    -0.06
     Lair
    -0.06
     будів
    -0.06
    сен
    -0.06
    POSITIVE LOGITS
    534
    0.06
     guitarist
    0.06
    Ctl
    0.06
    DAQ
    0.06
    !!,
    0.06
    equ
    0.06
    eguard
    0.06
    _IMP
    0.06
     ayn
    0.06
    _title
    0.06
    Act Density 0.007%

    No Known Activations