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

    Neuronpedia

    INDEX
    Explanations

    easy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    فل
    -0.07
    vfs
    -0.07
     Surveillance
    -0.07
    ращи
    -0.07
     theater
    -0.07
     politik
    -0.07
    /filter
    -0.07
     texture
    -0.06
    _boolean
    -0.06
     Dez
    -0.06
    POSITIVE LOGITS
    longitude
    0.06
     імен
    0.06
    routeParams
    0.06
     rehab
    0.06
     marginalized
    0.05
     película
    0.05
    지노
    0.05
    	LCD
    0.05
    pip
    0.05
     영화
    0.05
    Act Density 0.110%

    No Known Activations