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

    Neuronpedia

    INDEX
    Explanations

    alone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	FILE
    -0.07
    atitis
    -0.06
     emoc
    -0.06
    _UTF
    -0.06
     emotion
    -0.06
    ερό
    -0.06
     posterior
    -0.06
    -operator
    -0.06
    File
    -0.06
     incremental
    -0.06
    POSITIVE LOGITS
     synchronization
    0.07
     Benjamin
    0.07
     Merrill
    0.07
    。
    0.06
    ैं.↵
    0.06
    ****************************************
    0.06
    .↵
    0.06
    aby
    0.06
     packed
    0.06
     vra
    0.06
    Act Density 0.005%

    No Known Activations