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

    Neuronpedia

    INDEX
    Explanations

    conversational writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ชาต
    -0.07
     кожи
    -0.07
    KP
    -0.06
    .{
    -0.06
     ********
    -0.06
    ergy
    -0.06
    collision
    -0.06
    �
    -0.06
    анти
    -0.06
     kim
    -0.06
    POSITIVE LOGITS
    _REL
    0.06
     flavorful
    0.06
    reetings
    0.06
    INCLUDING
    0.06
     SON
    0.06
    ROP
    0.06
    Tracker
    0.06
     Населення
    0.06
    Attention
    0.06
    groupBox
    0.06
    Act Density 0.315%

    No Known Activations