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

    Neuronpedia

    INDEX
    Explanations

    inaugural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Berlin
    -0.07
    because
    -0.07
     Kre
    -0.07
    Fx
    -0.07
    지역
    -0.07
     chicago
    -0.07
     nuestros
    -0.06
    Lord
    -0.06
     Ferm
    -0.06
     traf
    -0.06
    POSITIVE LOGITS
    ARRIER
    0.06
    .ERR
    0.06
    .NaN
    0.06
    _LINUX
    0.06
    νω
    0.06
     Mae
    0.06
    _SAMPLES
    0.06
     Trout
    0.06
    UCH
    0.06
     Rahul
    0.06
    Act Density 0.005%

    No Known Activations