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

    Neuronpedia

    INDEX
    Explanations

    Sizes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    especially
    -0.07
    菍
    -0.07
     празд
    -0.07
     ebook
    -0.07
     jj
    -0.07
    德
    -0.07
     不
    -0.07
     delighted
    -0.06
     Ald
    -0.06
    ps
    -0.06
    POSITIVE LOGITS
    洿
    0.07
    .NEW
    0.07
    🛩
    0.07
    Built
    0.07
     культу
    0.07
     adversary
    0.06
    Constructed
    0.06
    _lifetime
    0.06
    쌰
    0.06
    .Raise
    0.06
    Act Density 0.061%

    No Known Activations