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

    Neuronpedia

    INDEX
    Explanations

    life support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rig
    -0.07
     طبقه
    -0.06
     переш
    -0.06
    ريم
    -0.06
    ,callback
    -0.06
     عب
    -0.06
     �
    -0.06
     juni
    -0.06
    ा.
    -0.06
    yun
    -0.06
    POSITIVE LOGITS
    即
    0.07
    _SYN
    0.06
     Sigma
    0.06
     adequate
    0.06
    _monitor
    0.06
     encountering
    0.06
    _HANDLER
    0.06
     ensure
    0.06
     currentDate
    0.06
    iah
    0.06
    Act Density 0.007%

    No Known Activations