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

    Neuronpedia

    INDEX
    Explanations

    loans, insurance, legal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proteins
    -0.07
    connection
    -0.07
     Hector
    -0.06
     ship
    -0.06
    .Movie
    -0.06
     Pride
    -0.06
    rones
    -0.06
     Preference
    -0.06
    çak
    -0.06
     policing
    -0.06
    POSITIVE LOGITS
    NON
    0.06
     mathematical
    0.06
    χο
    0.06
    _MAT
    0.06
    inant
    0.06
    	RTLR
    0.06
    ot
    0.06
    OT
    0.06
     Literary
    0.06
    ]bool
    0.06
    Act Density 0.089%

    No Known Activations