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

    Neuronpedia

    INDEX
    Explanations

    general

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cars
    -0.07
     Router
    -0.06
     kredi
    -0.06
    출
    -0.06
     [(
    -0.06
    -request
    -0.06
    -most
    -0.06
    Disk
    -0.06
    ındaki
    -0.06
    _hub
    -0.06
    POSITIVE LOGITS
    ]]:↵
    0.06
    ，该
    0.06
    оюз
    0.06
    Absolute
    0.06
     nervous
    0.06
     European
    0.06
    �
    0.06
    Representation
    0.06
     moderation
    0.06
    EndElement
    0.06
    Act Density 0.025%

    No Known Activations