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

    Neuronpedia

    INDEX
    Explanations

    love stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cute
    -0.06
    filme
    -0.06
    又
    -0.06
     Stage
    -0.06
     soft
    -0.06
     Funny
    -0.06
    crate
    -0.06
     який
    -0.06
     Lambda
    -0.06
     ICO
    -0.06
    POSITIVE LOGITS
     appropriated
    0.07
     understood
    0.07
    _gt
    0.07
    얼
    0.06
    32
    0.06
    exampleModalLabel
    0.06
    .sqrt
    0.06
     devel
    0.06
     Homeland
    0.06
    _logits
    0.06
    Act Density 0.002%

    No Known Activations