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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mare
    -0.08
    Subset
    -0.07
    dream
    -0.06
    ckpt
    -0.06
     feared
    -0.06
    Length
    -0.06
    ایر
    -0.06
    agini
    -0.06
    izzly
    -0.06
     Notes
    -0.06
    POSITIVE LOGITS
    268
    0.07
    _arguments
    0.07
    ActivityResult
    0.07
    ITHUB
    0.06
     japon
    0.06
    ButtonDown
    0.06
     geom
    0.06
    axis
    0.06
    れど
    0.06
     ·
    0.06
    Act Density 0.025%

    No Known Activations