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

    Neuronpedia

    INDEX
    Explanations

    waiting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ιστο
    -0.08
    ethers
    -0.08
     envisage
    -0.08
     يمكنك
    -0.08
     Calvin
    -0.07
     Alain
    -0.07
    "ג
    -0.07
     itib
    -0.07
    ാഗത
    -0.07
     Alessandro
    -0.07
    POSITIVE LOGITS
     reflective
    0.08
    的吗
    0.08
     inhibition
    0.07
    .Cancel
    0.07
     fillers
    0.07
     based
    0.07
     mierda
    0.07
    delay
    0.07
    _Ext
    0.07
     shipment
    0.07
    Act Density 0.001%

    No Known Activations