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

    Neuronpedia

    INDEX
    Explanations

    Numerical text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stranger
    -0.06
    logout
    -0.06
     ULONG
    -0.06
    Jar
    -0.06
    Tor
    -0.06
     zaz
    -0.06
    	request
    -0.06
     WS
    -0.06
    .mybatisplus
    -0.06
    nim
    -0.06
    POSITIVE LOGITS
     tattoos
    0.07
     En
    0.07
     policy
    0.07
     observations
    0.07
    owski
    0.06
     approximation
    0.06
     achieving
    0.06
     uphold
    0.06
    친
    0.06
     philosophy
    0.06
    Act Density 0.071%

    No Known Activations