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

    Neuronpedia

    INDEX
    Explanations

    -ray

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แนว
    -0.08
     dsp
    -0.07
    searchModel
    -0.07
     success
    -0.07
    三大
    -0.07
    ��
    -0.07
     ('$
    -0.07
    TMP
    -0.06
     Table
    -0.06
     Bene
    -0.06
    POSITIVE LOGITS
     anyways
    0.08
    浏览器
    0.07
    -abortion
    0.07
    apist
    0.07
     Zimmerman
    0.07
    杳
    0.07
    Witness
    0.06
     Photography
    0.06
    Cómo
    0.06
     Cage
    0.06
    Act Density 0.003%

    No Known Activations