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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sessions
    -0.06
     Prayer
    -0.06
    _TOGGLE
    -0.06
    rupa
    -0.06
    ٤
    -0.06
    ٣
    -0.06
     Elm
    -0.06
    tmp
    -0.06
     пля
    -0.06
    二
    -0.06
    POSITIVE LOGITS
    .array
    0.07
     支
    0.07
     stehen
    0.07
    icopt
    0.06
    /********************************
    0.06
     transforms
    0.06
    loven
    0.06
     dut
    0.06
     STATUS
    0.06
    oused
    0.06
    Act Density 0.012%

    No Known Activations