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

    Neuronpedia

    INDEX
    Explanations

    group membership

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Coal
    -0.07
     afford
    -0.07
     Horizon
    -0.07
     THR
    -0.07
     breve
    -0.07
     Ug
    -0.06
    inating
    -0.06
     aos
    -0.06
     rio
    -0.06
     λεπ
    -0.06
    POSITIVE LOGITS
     mne
    0.06
    �
    0.06
    ;&
    0.06
     organizational
    0.06
     descendant
    0.06
    ointment
    0.06
    :nil
    0.06
    \Block
    0.06
    /autoload
    0.06
    ‌م
    0.06
    Act Density 0.078%

    No Known Activations