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

    Neuronpedia

    INDEX
    Explanations

    hello

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @d
    -0.07
    Space
    -0.07
    Seed
    -0.07
     数
    -0.07
    投
    -0.06
    ^n
    -0.06
    Part
    -0.06
    FormControl
    -0.06
    /REC
    -0.06
    proc
    -0.06
    POSITIVE LOGITS
     Hey
    0.08
     Hello
    0.08
    stairs
    0.07
    LO
    0.07
    ledge
    0.07
     cele
    0.07
     jež
    0.07
     Bye
    0.07
    _hello
    0.07
    گو
    0.07
    Act Density 0.016%

    No Known Activations