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

    Neuronpedia

    INDEX
    Explanations

    online information sources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    笳
    -0.07
     }}
    -0.07
    <option
    -0.07
     spacer
    -0.07
     Wit
    -0.07
    -metadata
    -0.07
     בספר
    -0.06
     '{{
    -0.06
    }]
    -0.06
    _workspace
    -0.06
    POSITIVE LOGITS
     copyright
    0.07
     foreign
    0.07
    *B
    0.07
    褶
    0.07
     Barnett
    0.07
     Online
    0.07
    מקד
    0.07
    גידול
    0.07
    เสนอ
    0.06
    PostMapping
    0.06
    Act Density 0.016%

    No Known Activations