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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /me
    -0.09
     lighting
    -0.08
    itado
    -0.08
    leyen
    -0.07
     initialise
    -0.07
    аторы
    -0.07
     Initialise
    -0.07
     питания
    -0.07
     Lighting
    -0.07
    -0.07
    POSITIVE LOGITS
     fragile
    0.10
     precar
    0.09
    _ATTACH
    0.09
     cling
    0.09
    Attachment
    0.09
    Attachments
    0.09
     relinqu
    0.08
    .attach
    0.08
     आग्रह
    0.08
     attachment
    0.08
    Act Density 0.022%
    No Known Activations