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

    Neuronpedia

    INDEX
    Explanations

    pole

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conf
    -0.09
    Conf
    -0.08
    advance
    -0.08
    ste
    -0.08
    conf
    -0.08
    erc
    -0.07
    .Memory
    -0.07
    .experimental
    -0.07
    Advanced
    -0.07
    ক্ষম
    -0.07
    POSITIVE LOGITS
     odpow
    0.10
     correspondente
    0.09
    对应
    0.09
    אָר
    0.09
     जंगल
    0.09
     correspondiente
    0.08
     tweeted
    0.08
     promot
    0.08
     Marun
    0.08
     corresponding
    0.08
    Act Density 0.001%

    No Known Activations