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

    Neuronpedia

    INDEX
    Explanations

    Spain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endorsing
    -0.06
    inds
    -0.06
    Indented
    -0.06
    arsing
    -0.06
     Practices
    -0.06
    "G
    -0.06
     unlawful
    -0.06
    qualities
    -0.06
    _Vector
    -0.06
    -0.06
    POSITIVE LOGITS
    道
    0.08
    空
    0.07
    divide
    0.07
    /Object
    0.06
     dataSnapshot
    0.06
    선
    0.06
    Feb
    0.06
    一般
    0.06
     Joined
    0.06
     redo
    0.06
    Act Density 0.000%

    No Known Activations