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

    Neuronpedia

    INDEX
    Explanations

    associated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incur
    -0.07
     SOL
    -0.06
     ['.
    -0.06
    -state
    -0.06
    ados
    -0.06
     states
    -0.06
     sensational
    -0.06
    wicklung
    -0.06
    .bin
    -0.06
     "|
    -0.06
    POSITIVE LOGITS
     vysvět
    0.07
    _cuda
    0.06
    YZ
    0.06
    ایش
    0.06
    registers
    0.06
    иты
    0.06
    IK
    0.06
     Verified
    0.06
    ческое
    0.06
    дя
    0.06
    Act Density 0.023%

    No Known Activations