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

    Neuronpedia

    INDEX
    Explanations

    structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     können
    -0.07
    decoded
    -0.07
    清晰
    -0.07
     Bene
    -0.07
     signin
    -0.07
    奸
    -0.07
     declined
    -0.06
    Like
    -0.06
    讷
    -0.06
    𝐍
    -0.06
    POSITIVE LOGITS
    ropri
    0.06
    葡萄牙
    0.06
     Represent
    0.06
    postgresql
    0.06
    species
    0.06
    .virtual
    0.06
    (instruction
    0.06
    (pub
    0.06
    (kernel
    0.06
    abbr
    0.06
    Act Density 0.000%

    No Known Activations