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

    Neuronpedia

    INDEX
    Explanations

    single

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ительных
    -0.07
     infusion
    -0.07
    akers
    -0.06
    -chair
    -0.06
     promoters
    -0.06
     ol
    -0.06
    _description
    -0.06
    Release
    -0.06
     lament
    -0.06
    ่งข
    -0.06
    POSITIVE LOGITS
     single
    0.10
     Single
    0.09
    ツ
    0.07
     pint
    0.06
    .pub
    0.06
    ?)↵↵
    0.06
     Lesb
    0.06
     SINGLE
    0.06
    调整
    0.06
    -=
    0.06
    Act Density 0.010%

    No Known Activations