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
     negativity
    -0.07
     \$
    -0.07
     Sang
    -0.07
    ByteBuffer
    -0.07
     راه
    -0.06
    ,opt
    -0.06
     αυτή
    -0.06
     hiển
    -0.06
     Hogwarts
    -0.06
    SX
    -0.06
    POSITIVE LOGITS
    matic
    0.07
    tener
    0.06
     rose
    0.06
     unus
    0.06
     readings
    0.06
    ثير
    0.06
    isme
    0.06
    _Dep
    0.06
    ||(
    0.06
    论
    0.06
    Act Density 0.000%

    No Known Activations