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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מלח
    -0.07
    �
    -0.07
     teaser
    -0.07
    .lastname
    -0.07
     youtube
    -0.07
    .head
    -0.07
     möchte
    -0.07
    痤
    -0.07
     coll
    -0.07
     Privacy
    -0.07
    POSITIVE LOGITS
    ها
    0.07
    .SEVER
    0.06
    ION
    0.06
    ARY
    0.06
    挂号
    0.06
    TS
    0.06
    hof
    0.06
    砀
    0.06
    酡
    0.06
    绽放
    0.06
    Act Density 0.010%

    No Known Activations