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

    Neuronpedia

    INDEX
    Explanations

    Redistributions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     controls
    -0.07
     нашей
    -0.07
    ptoms
    -0.06
     TVs
    -0.06
     Tort
    -0.06
     Controls
    -0.06
     obed
    -0.06
     WCS
    -0.06
     lust
    -0.06
     “…
    -0.06
    POSITIVE LOGITS
    endphp
    0.07
    �
    0.06
    _LANGUAGE
    0.06
    (cx
    0.06
    _hd
    0.06
    .getState
    0.06
    Congratulations
    0.06
    =read
    0.06
    ịa
    0.06
     elbow
    0.06
    Act Density 0.000%

    No Known Activations