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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dispose
    -0.27
     Dispose
    -0.27
    çİ©æ³ķ
    -0.26
     coolest
    -0.25
    RegExp
    -0.25
    ä¸Ģå¤ľ
    -0.25
    orgia
    -0.24
    ISM
    -0.24
    éĥ¨ä»¶
    -0.24
    å½¢çĬ¶
    -0.24
    POSITIVE LOGITS
    ieber
    0.28
    请çĤ¹åĩ»
    0.27
    ircon
    0.26
    cott
    0.26
    requested
    0.26
    erver
    0.25
    Universal
    0.25
    pic
    0.24
    ,:,:
    0.24
    agher
    0.24
    Act Density 2.142%

    No Known Activations