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

    Neuronpedia

    INDEX
    Explanations

    personal experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poil
    -0.07
     pastors
    -0.07
    _EP
    -0.07
    /py
    -0.06
     indicted
    -0.06
    itler
    -0.06
     showToast
    -0.06
     낮
    -0.06
    ,idx
    -0.06
     vaz
    -0.06
    POSITIVE LOGITS
     remembered
    0.06
    。それ
    0.06
    Inform
    0.06
    šť
    0.06
     Recogn
    0.06
     Holds
    0.06
     Buf
    0.06
     narration
    0.06
     Kens
    0.06
     asynchronously
    0.06
    Act Density 0.029%

    No Known Activations