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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stones
    -0.07
    .ctrl
    -0.07
     floats
    -0.07
     networking
    -0.07
     friendship
    -0.07
     Point
    -0.07
     rocky
    -0.06
     belongs
    -0.06
    .js
    -0.06
    _inventory
    -0.06
    POSITIVE LOGITS
    }');↵
    0.06
    :^(
    0.06
    ิลป
    0.06
    Ả
    0.06
    chema
    0.06
     реє
    0.06
    θε
    0.06
     Vladim
    0.05
    ]},↵
    0.05
    ("")]↵
    0.05
    Act Density 0.018%

    No Known Activations