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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prevention
    -0.07
    XmlElement
    -0.07
    anes
    -0.07
     shrimp
    -0.07
    edl
    -0.07
     phục
    -0.06
    уп
    -0.06
    uegos
    -0.06
     distort
    -0.06
     shepherd
    -0.06
    POSITIVE LOGITS
    _escape
    0.07
    contact
    0.07
    ('/:
    0.06
    .Messages
    0.06
    Pale
    0.06
    ]()↵
    0.06
    vik
    0.06
     ราค
    0.06
    .':
    0.06
     Located
    0.06
    Act Density 0.005%

    No Known Activations