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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ================================================
    -0.06
    .Account
    -0.06
    _nsec
    -0.06
    �
    -0.06
    iem
    -0.06
     blades
    -0.06
     Geo
    -0.06
     Dez
    -0.06
    ancybox
    -0.06
    Deg
    -0.05
    POSITIVE LOGITS
    	payload
    0.07
    OPEN
    0.07
    icap
    0.07
    (property
    0.07
    .visible
    0.07
    .nih
    0.07
    mis
    0.07
    MD
    0.06
    letic
    0.06
    рав
    0.06
    Act Density 0.000%

    No Known Activations