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

    Neuronpedia

    INDEX
    Explanations

    handle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Experiment
    -0.07
    IFY
    -0.07
     crc
    -0.06
     cyst
    -0.06
    itic
    -0.06
     perg
    -0.06
     excerpt
    -0.06
     checklist
    -0.06
    Progress
    -0.06
    _percent
    -0.06
    POSITIVE LOGITS
     handle
    0.13
     handled
    0.11
     handling
    0.11
     Handle
    0.11
    handle
    0.10
     handles
    0.10
     Handling
    0.09
    -handle
    0.09
     handleClose
    0.09
     �
    0.09
    Act Density 0.028%

    No Known Activations