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

    Neuronpedia

    INDEX
    Explanations

    Explaining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     значення
    -0.07
    猛
    -0.06
    قی
    -0.06
    astic
    -0.06
     tạo
    -0.06
    QM
    -0.06
     ΚΑΙ
    -0.06
    parameters
    -0.06
     quotid
    -0.06
    łe
    -0.06
    POSITIVE LOGITS
    )(__
    0.08
    	Expect
    0.07
    br
    0.07
    -products
    0.07
    Bl
    0.06
    caps
    0.06
    ickname
    0.06
     "-
    0.06
     Slo
    0.06
     ventures
    0.06
    Act Density 0.050%

    No Known Activations