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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gui
    -0.07
     CPC
    -0.07
     Gentle
    -0.07
    _Object
    -0.06
    _bottom
    -0.06
     Proj
    -0.06
     Flush
    -0.06
     collaps
    -0.06
     els
    -0.06
     Concent
    -0.06
    POSITIVE LOGITS
     attacker
    0.07
     campaigners
    0.07
     listened
    0.07
    ,:);↵
    0.06
     artır
    0.06
    Commercial
    0.06
    など
    0.06
    [this
    0.06
     GUIDATA
    0.06
    tokenizer
    0.06
    Act Density 0.002%

    No Known Activations