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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SYNC
    -0.07
     CONTROL
    -0.06
    ]").
    -0.06
    Creative
    -0.06
    composite
    -0.06
     �
    -0.06
    =>$
    -0.06
    _stage
    -0.06
    OMP
    -0.06
    _train
    -0.06
    POSITIVE LOGITS
     중
    0.07
     (/
    0.06
    辰
    0.06
     acronym
    0.06
     convo
    0.06
    一年
    0.06
    redients
    0.06
     用
    0.06
    款
    0.06
     FIRST
    0.06
    Act Density 0.000%

    No Known Activations