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

    Neuronpedia

    INDEX
    Explanations

    switch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     checkpoints
    -0.08
     chains
    -0.07
    Head
    -0.07
    招聘
    -0.07
    ]],
    -0.07
    节
    -0.07
    [level
    -0.07
     astonished
    -0.07
    �
    -0.07
    notes
    -0.06
    POSITIVE LOGITS
    ATT
    0.07
     Thief
    0.06
    arch
    0.06
    .MenuItem
    0.06
     cocci
    0.06
    Publisher
    0.06
     خورد
    0.06
    jsx
    0.06
     Gard
    0.06
     fait
    0.06
    Act Density 0.004%

    No Known Activations