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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ารย
    -0.07
    (stack
    -0.06
    dirs
    -0.06
    _edit
    -0.06
    .role
    -0.06
     Ore
    -0.06
    //-
    -0.06
     Btn
    -0.06
     Dry
    -0.06
     brig
    -0.06
    POSITIVE LOGITS
     histor
    0.07
    aining
    0.06
     evaluating
    0.06
    /class
    0.06
     наб
    0.06
    (addr
    0.06
    (secret
    0.06
    еред
    0.06
    Tahoma
    0.06
    ové
    0.06
    Act Density 0.012%

    No Known Activations