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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mối
    -0.06
     tem
    -0.06
    _Final
    -0.06
    ρούν
    -0.06
     rm
    -0.06
     может
    -0.06
    iah
    -0.05
    _PROJECT
    -0.05
    Yo
    -0.05
     Launcher
    -0.05
    POSITIVE LOGITS
    0.07
     Machine
    0.07
    途
    0.06
     Hairst
    0.06
    ��
    0.06
     cooldown
    0.06
    0.06
     cleans
    0.06
    076
    0.06
     نوع
    0.06
    Act Density 0.000%

    No Known Activations