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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roads
    -0.08
    becca
    -0.07
    _memory
    -0.07
    elligence
    -0.07
    _width
    -0.06
    цями
    -0.06
     sonrasında
    -0.06
    batch
    -0.06
     �
    -0.06
     newer
    -0.06
    POSITIVE LOGITS
    altung
    0.06
     mech
    0.06
    ूष
    0.06
    /lab
    0.06
    heid
    0.06
     subt
    0.06
    ckså
    0.06
     cid
    0.06
     Shopping
    0.06
     informing
    0.06
    Act Density 0.107%

    No Known Activations