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
     subj
    -0.07
    ITTE
    -0.07
     Hydraulic
    -0.07
     ingen
    -0.07
     Heater
    -0.06
     oyun
    -0.06
    頓
    -0.06
    _ROW
    -0.06
     gram
    -0.06
    ottle
    -0.06
    POSITIVE LOGITS
                                                    ↵
    0.06
    ливі
    0.06
    -job
    0.06
    							
↵
    0.06
    \Twig
    0.06
     Solic
    0.06
     HASH
    0.06
    پس
    0.06
    )"↵
    0.06
    Feb
    0.05
    Act Density 0.004%

    No Known Activations