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

    Neuronpedia

    INDEX
    Explanations

    var

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    berries
    -0.07
     Rape
    -0.07
    estr
    -0.06
     dime
    -0.06
     Living
    -0.06
     insp
    -0.06
     ус
    -0.06
     Walter
    -0.06
    mor
    -0.06
    .publish
    -0.06
    POSITIVE LOGITS
    itimate
    0.07
    }*/↵
    0.07
     ничего
    0.07
    がない
    0.06
    μένου
    0.06
    AIT
    0.06
    ماری
    0.06
     """
↵
↵
    0.06
    undy
    0.06
    culator
    0.06
    Act Density 0.007%

    No Known Activations