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

    Neuronpedia

    INDEX
    Explanations

    software errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ypical
    -0.08
    ReceiveProps
    -0.07
    Sharper
    -0.07
     постав
    -0.06
    慎
    -0.06
     Any
    -0.06
     Stark
    -0.06
     دوره
    -0.06
     setPassword
    -0.06
    龙
    -0.06
    POSITIVE LOGITS
     Percent
    0.07
    ags
    0.07
    _SEARCH
    0.07
    -Control
    0.07
    fell
    0.06
    _PC
    0.06
    uvw
    0.06
     privilege
    0.06
     PET
    0.06
     Vic
    0.06
    Act Density 0.005%

    No Known Activations