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

    Neuronpedia

    INDEX
    Explanations

    parentheses and underscores

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    蝾
    -0.08
     baking
    -0.07
    RuntimeObject
    -0.07
     Ron
    -0.07
    怦
    -0.07
    erture
    -0.07
    _pro
    -0.06
    嗞
    -0.06
     particle
    -0.06
    景区
    -0.06
    POSITIVE LOGITS
     detailed
    0.08
    䥽
    0.08
    tell
    0.07
     모르
    0.07
    Possible
    0.07
    /get
    0.06
     grim
    0.06
    大使
    0.06
     woes
    0.06
     Marketplace
    0.06
    Act Density 0.040%

    No Known Activations