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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tapes
    -0.06
     instantiated
    -0.06
    (batch
    -0.06
     نیست
    -0.06
    .showMessageDialog
    -0.06
    uctor
    -0.06
    onth
    -0.05
     огра
    -0.05
    การแข
    -0.05
     přid
    -0.05
    POSITIVE LOGITS
    itecture
    0.08
     tỉ
    0.07
    金
    0.07
    該
    0.07
    AI
    0.07
     giới
    0.07
    FAQ
    0.07
     xxx
    0.07
    .News
    0.07
    charged
    0.06
    Act Density 0.000%

    No Known Activations