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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ubuntu
    -0.07
     Gard
    -0.06
     craft
    -0.06
    Absolute
    -0.06
    滿
    -0.06
     poetry
    -0.06
    vik
    -0.06
     موج
    -0.06
     passages
    -0.06
     puzzles
    -0.06
    POSITIVE LOGITS
    ftype
    0.07
    Structured
    0.06
     Serve
    0.06
     pinnacle
    0.06
    mailbox
    0.06
    	Spring
    0.06
    (handler
    0.06
    _goals
    0.06
    Secret
    0.06
    净
    0.06
    Act Density 0.000%

    No Known Activations