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

    Neuronpedia

    INDEX
    Explanations

    variations among different conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Every
    -0.07
     merged
    -0.07
    вают
    -0.06
    uers
    -0.06
    sticks
    -0.06
    _tc
    -0.06
     *(
    -0.06
    他們
    -0.06
     Writer
    -0.06
     columns
    -0.06
    POSITIVE LOGITS
     vedení
    0.06
    凉
    0.06
     Netanyahu
    0.06
     incontr
    0.06
     Relay
    0.06
     Trotsky
    0.06
     Alexand
    0.05
    anyahu
    0.05
     Bellev
    0.05
    _Project
    0.05
    Act Density 0.054%

    No Known Activations