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

    Neuronpedia

    INDEX
    Explanations

    software testing/dependencies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мг
    -0.07
     Pointer
    -0.06
    "{
    -0.06
     Lý
    -0.06
    205
    -0.06
    `]
    -0.06
     Language
    -0.06
     obt
    -0.06
     command
    -0.06
     Те
    -0.06
    POSITIVE LOGITS
    _NEXT
    0.07
    ──
    0.07
    asz
    0.06
     hayal
    0.06
    анием
    0.06
    <section
    0.06
    _CONF
    0.06
    _marker
    0.06
    .rot
    0.06
    |--------------------------------------------------------------------------↵
    0.06
    Act Density 0.013%

    No Known Activations