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

    Neuronpedia

    INDEX
    Explanations

    Meeting standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    might
    -0.06
    _ONE
    -0.06
    У
    -0.06
    陰
    -0.06
    _TYPES
    -0.06
     У
    -0.06
    Phones
    -0.06
    temperature
    -0.06
     complications
    -0.06
    _Pods
    -0.06
    POSITIVE LOGITS
    _ft
    0.07
     offsetof
    0.06
     "'");↵
    0.06
    	perror
    0.06
     destabil
    0.06
    (er
    0.06
     dra
    0.06
     fert
    0.06
     derec
    0.06
    áci
    0.06
    Act Density 0.020%

    No Known Activations