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

    Neuronpedia

    INDEX
    Explanations

    OD ND codes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     VH
    0.60
     VX
    0.59
    isto
    0.56
     आईएफ
    0.55
     Ispol
    0.54
    abinieri
    0.51
     AX
    0.50
    getCql
    0.50
     bureaucratic
    0.50
     dach
    0.50
    POSITIVE LOGITS
    OD
    0.98
     OD
    0.95
    ND
    0.91
    Nz
    0.91
    ODM
    0.90
    ODB
    0.88
    NDE
    0.88
    ODE
    0.84
    NG
    0.83
     NG
    0.83
    Act Density 0.001%

    No Known Activations