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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cycle
    -0.07
     spatial
    -0.07
    .functions
    -0.06
     restraint
    -0.06
     Favorite
    -0.06
     effect
    -0.06
     abnormalities
    -0.06
     INDIRECT
    -0.06
     záv
    -0.06
     Met
    -0.06
    POSITIVE LOGITS
     Mods
    0.07
     rises
    0.07
     hw
    0.07
    unny
    0.06
     (>
    0.06
    رسی
    0.06
     sketches
    0.06
    gin
    0.06
    ][$
    0.06
     pense
    0.06
    Act Density 0.001%

    No Known Activations