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

    Neuronpedia

    INDEX
    Explanations

    throw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McCoy
    -0.07
    DEX
    -0.07
    .effect
    -0.06
    ポイント
    -0.06
    üme
    -0.06
    -plugin
    -0.06
     meg
    -0.06
     сут
    -0.06
    TRA
    -0.06
     disputes
    -0.06
    POSITIVE LOGITS
     "*"
    0.07
    _'
    0.06
    ]*(
    0.06
    -fast
    0.06
    egrated
    0.06
     اینکه
    0.06
     hell
    0.06
    egree
    0.06
    *:
    0.06
    addGroup
    0.06
    Act Density 0.010%

    No Known Activations