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

    Neuronpedia

    INDEX
    Explanations

    scenario, bug, game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     authorised
    0.55
     receivables
    0.50
     па
    0.48
     resetting
    0.48
     отли
    0.47
     recomendable
    0.47
     entrer
    0.46
     communication
    0.46
     debes
    0.46
     inviting
    0.46
    POSITIVE LOGITS
    Fields
    0.47
    et
    0.47
    Method
    0.47
    顿
    0.46
    or
    0.45
    Plot
    0.45
    Role
    0.44
    Mesh
    0.44
    em
    0.44
    Properties
    0.44
    Act Density 0.002%

    No Known Activations