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

    Neuronpedia

    INDEX
    Explanations

    misinformation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xcb
    -0.06
     ump
    -0.06
    Ipv
    -0.06
    dba
    -0.06
     khó
    -0.06
     YAML
    -0.06
    ــــــــ
    -0.06
    Label
    -0.06
    icit
    -0.06
    mnop
    -0.06
    POSITIVE LOGITS
     �
    0.06
     procedure
    0.06
     NSW
    0.06
    madan
    0.06
     factory
    0.06
    リカ
    0.06
    Human
    0.06
     Prism
    0.06
    σο
    0.06
     Schwe
    0.06
    Act Density 0.002%

    No Known Activations