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

    Neuronpedia

    INDEX
    Explanations

    API usage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Children
    -0.07
    	headers
    -0.07
    sets
    -0.06
     sets
    -0.06
    Down
    -0.06
    LOWER
    -0.06
    marginLeft
    -0.06
    ót
    -0.06
    �
    -0.06
     shocks
    -0.06
    POSITIVE LOGITS
    0.07
     blogs
    0.06
     rej
    0.06
     Alic
    0.06
    ąż
    0.06
     Ramos
    0.06
    _construct
    0.06
     bourgeois
    0.06
    rı
    0.06
     /****************************************************************
    0.06
    Act Density 0.099%

    No Known Activations