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

    Neuronpedia

    INDEX
    Explanations

    dictionary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Run
    -0.07
    =yes
    -0.07
     Lone
    -0.07
    ne
    -0.07
     ❤
    -0.07
    orne
    -0.07
     vå
    -0.07
     experiencia
    -0.07
     Palestine
    -0.07
    avelength
    -0.07
    POSITIVE LOGITS
     Dict
    0.11
     dictionary
    0.10
    Dictionary
    0.10
     dictionaries
    0.09
     dictates
    0.09
     diary
    0.09
    (dict
    0.09
     dict
    0.09
    dict
    0.09
    =dict
    0.09
    Act Density 0.016%

    No Known Activations