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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IRCLE
    -0.06
    Specifications
    -0.06
    ManagedObject
    -0.06
    	LOG
    -0.06
     Headquarters
    -0.06
    Cal
    -0.06
     plotting
    -0.06
     pants
    -0.06
    contacts
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     hỏi
    0.07
    없이
    0.06
     Bbw
    0.06
    (dw
    0.06
    .drag
    0.06
    ignon
    0.06
    (inflater
    0.06
    (pt
    0.06
    (Enum
    0.06
    ortic
    0.06
    Act Density 0.073%

    No Known Activations