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

    Neuronpedia

    INDEX
    Explanations

    Spying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Unauthorized
    -0.07
     memoria
    -0.06
     MMO
    -0.06
     unclear
    -0.06
     ورز
    -0.06
     οποίο
    -0.06
    _MEM
    -0.06
    经营
    -0.06
    具体
    -0.06
    폭
    -0.06
    POSITIVE LOGITS
     Venom
    0.07
     []
↵
    0.06
    yclerview
    0.06
     jars
    0.06
     psychiatrist
    0.06
     Ky
    0.06
     žena
    0.06
     pillows
    0.06
    ='',↵
    0.06
    oller
    0.06
    Act Density 0.036%

    No Known Activations