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

    Neuronpedia

    INDEX
    Explanations

    League

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "go
    -0.07
    �
    -0.06
    -tested
    -0.06
     Automotive
    -0.06
    _MOV
    -0.06
    言葉
    -0.06
    ￣￣
    -0.06
    _Element
    -0.06
    +↵↵
    -0.06
    NewItem
    -0.06
    POSITIVE LOGITS
     Conor
    0.07
     archetype
    0.07
    one
    0.06
     counterpart
    0.06
    cone
    0.06
     BLACK
    0.06
     cape
    0.06
    Conflict
    0.06
     trail
    0.06
    ATA
    0.06
    Act Density 0.000%

    No Known Activations