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

    Neuronpedia

    INDEX
    Explanations

    great

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ацион
    -0.08
    icie
    -0.07
    _average
    -0.07
     arrive
    -0.06
    أجر
    -0.06
    入驻
    -0.06
    vpn
    -0.06
    傍晚
    -0.06
    ishes
    -0.06
    ertime
    -0.06
    POSITIVE LOGITS
     flatt
    0.07
     HEX
    0.07
    .fm
    0.07
     khách
    0.07
     TRACK
    0.07
     Validators
    0.07
    属
    0.06
     Garden
    0.06
     offic
    0.06
     Flor
    0.06
    Act Density 0.029%

    No Known Activations