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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    픠
    -0.08
    MISSION
    -0.07
     случа
    -0.07
     institution
    -0.07
    _missing
    -0.06
     vacancy
    -0.06
    _literals
    -0.06
    making
    -0.06
     HEIGHT
    -0.06
    CHANGE
    -0.06
    POSITIVE LOGITS
    抱团
    0.07
    ạp
    0.07
     boxed
    0.07
    _ops
    0.07
     observ
    0.07
     An
    0.06
    artial
    0.06
    茨
    0.06
    'A
    0.06
    -an
    0.06
    Act Density 0.033%

    No Known Activations