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

    Neuronpedia

    INDEX
    Explanations

    is/are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     जनवर
    -0.07
    ladu
    -0.07
     globe
    -0.07
    Statement
    -0.07
     contradict
    -0.07
    /read
    -0.07
     înt
    -0.06
    edish
    -0.06
     jedna
    -0.06
     repos
    -0.06
    POSITIVE LOGITS
    کری
    0.06
    osyal
    0.06
     �
    0.06
     виход
    0.06
     愛
    0.06
     Ventures
    0.06
    Visualization
    0.06
    ення
    0.06
     Air
    0.06
     unhappy
    0.06
    Act Density 0.056%

    No Known Activations