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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intending
    -0.08
     sidel
    -0.06
     open
    -0.06
     доход
    -0.06
    SELF
    -0.06
     �
    -0.06
    plets
    -0.06
     desires
    -0.06
     Functional
    -0.06
     fert
    -0.06
    POSITIVE LOGITS
    処
    0.07
    سام
    0.07
    sequential
    0.07
    _deposit
    0.07
    \Database
    0.07
     oslo
    0.07
    ))?
    0.06
     SS
    0.06
    ]!='
    0.06
    ])).
    0.06
    Act Density 0.007%

    No Known Activations