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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Plane
    -0.07
     возмож
    -0.06
     Pare
    -0.06
     않
    -0.06
    erin
    -0.06
    Pale
    -0.06
     Embed
    -0.06
    _party
    -0.06
     bern
    -0.06
    нь
    -0.06
    POSITIVE LOGITS
    裝
    0.07
     seul
    0.06
     RequestContext
    0.06
     temiz
    0.06
     Waterproof
    0.06
     Zub
    0.06
     IDS
    0.06
    tor
    0.06
    \application
    0.06
     Friendship
    0.06
    Act Density 0.007%

    No Known Activations