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

    Neuronpedia

    INDEX
    Explanations

    Beginning of varied discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PDF
    -0.07
    division
    -0.06
    ρός
    -0.06
     Creation
    -0.06
    虎
    -0.06
    ku
    -0.06
    ALS
    -0.06
    .sig
    -0.06
    Document
    -0.06
    tas
    -0.06
    POSITIVE LOGITS
    }");↵
    0.08
     действительно
    0.06
     welche
    0.06
     laps
    0.06
    .reserve
    0.06
     STOCK
    0.06
     OP
    0.06
    िरफ
    0.06
     overcome
    0.06
    ]!=
    0.06
    Act Density 0.027%

    No Known Activations