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

    Neuronpedia

    INDEX
    Explanations

    composition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dings
    -0.06
    INPUT
    -0.06
    pNet
    -0.06
    government
    -0.06
    �
    -0.06
    _Thread
    -0.06
    Color
    -0.06
     polarization
    -0.06
    Emoji
    -0.06
     danger
    -0.06
    POSITIVE LOGITS
     composition
    0.09
     compositions
    0.08
     залиш
    0.07
    하며
    0.07
    ni
    0.07
     그러나
    0.07
     Catherine
    0.07
    callable
    0.07
    .","
    0.07
     。↵
    0.07
    Act Density 0.002%

    No Known Activations