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

    Neuronpedia

    INDEX
    Explanations

    tutorials and guides

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    queries
    -0.07
    Group
    -0.07
    носят
    -0.07
    Marker
    -0.07
    Effects
    -0.06
     yıl
    -0.06
    ues
    -0.06
    mana
    -0.06
    =line
    -0.06
     wives
    -0.06
    POSITIVE LOGITS
    subscriber
    0.06
     createdAt
    0.06
     cybersecurity
    0.06
    _ARCH
    0.06
     writeln
    0.06
     profits
    0.06
    -de
    0.06
     <!
    0.06
     än
    0.06
     textDecoration
    0.06
    Act Density 0.036%

    No Known Activations