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

    Neuronpedia

    INDEX
    Explanations

    share

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Saw
    -0.08
     illness
    -0.08
     distro
    -0.07
    Voc
    -0.07
     Fabulous
    -0.07
     связь
    -0.07
    িস্থ
    -0.07
    ,de
    -0.07
     阅读
    -0.07
     strategi
    -0.07
    POSITIVE LOGITS
     thermique
    0.08
     sue
    0.07
     hid
    0.07
    Frm
    0.07
    孔
    0.07
     castell
    0.07
    ها
    0.07
     komo
    0.07
    holder
    0.07
     sp
    0.07
    Act Density 0.011%

    No Known Activations