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

    Neuronpedia

    INDEX
    Explanations

    Industry standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้อง
    -0.07
     Prison
    -0.07
     IU
    -0.07
     Chan
    -0.07
    _Blue
    -0.07
     بين
    -0.06
    IU
    -0.06
    级
    -0.06
    %).
    -0.06
     Weapons
    -0.06
    POSITIVE LOGITS
    转载请
    0.07
     germany
    0.07
    سعادة
    0.07
    _FOLDER
    0.07
     aesthetics
    0.06
    Gesture
    0.06
     JSBracketAccess
    0.06
    🖌
    0.06
     unserialize
    0.06
     fputs
    0.06
    Act Density 0.094%

    No Known Activations