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

    Neuronpedia

    INDEX
    Explanations

    injuries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yön
    -0.07
     près
    -0.07
    ================================================================================
    -0.07
     Redemption
    -0.06
    Transition
    -0.06
    COMMAND
    -0.06
     '';↵↵
    -0.06
    _TRA
    -0.06
    δρα
    -0.06
    ・・
    -0.06
    POSITIVE LOGITS
     toolbar
    0.06
     partners
    0.06
     Affordable
    0.06
    emat
    0.06
    	ctrl
    0.06
     Shen
    0.06
    ivating
    0.06
     fingerprint
    0.06
    -li
    0.06
     smashed
    0.06
    Act Density 0.010%

    No Known Activations