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

    Neuronpedia

    INDEX
    Explanations

    community

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ponential
    -0.07
    \\\\
    -0.07
     Π
    -0.07
    품
    -0.06
    {k
    -0.06
     inhibitors
    -0.06
     К
    -0.06
    ↵			↵
    -0.06
    onte
    -0.06
     toilets
    -0.06
    POSITIVE LOGITS
     mach
    0.07
     charms
    0.07
    rowser
    0.06
     raspberry
    0.06
     booze
    0.06
    Sn
    0.06
    _spaces
    0.06
    duct
    0.06
     MAL
    0.06
     Revised
    0.06
    Act Density 0.130%

    No Known Activations