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

    Neuronpedia

    INDEX
    Explanations

    dependence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IData
    -0.07
     fileSize
    -0.07
     Domain
    -0.07
    436
    -0.07
     Bone
    -0.07
    -app
    -0.07
     pall
    -0.07
    -runtime
    -0.07
    Having
    -0.06
    ��作
    -0.06
    POSITIVE LOGITS
     モ
    0.06
     punishments
    0.05
    }->
    0.05
     stretching
    0.05
     atd
    0.05
    販
    0.05
     reconoc
    0.05
     algae
    0.05
    _SEQUENCE
    0.05
     visuals
    0.05
    Act Density 0.023%

    No Known Activations