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

    Neuronpedia

    INDEX
    Explanations

    mood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    教授
    -0.07
     Ont
    -0.07
    raw
    -0.07
    -distance
    -0.06
     ReadOnly
    -0.06
     respective
    -0.06
    vault
    -0.06
     facility
    -0.06
     Tablet
    -0.06
    िट
    -0.06
    POSITIVE LOGITS
     mood
    0.10
    (hdr
    0.07
     Mood
    0.07
     cheered
    0.07
     Cong
    0.07
    (adapter
    0.07
     �
    0.07
     voters
    0.07
     созд
    0.07
     ((_
    0.06
    Act Density 0.006%

    No Known Activations