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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obedient
    -0.07
     worse
    -0.07
     =~
    -0.07
     suing
    -0.06
     Mon
    -0.06
     nurs
    -0.06
     місто
    -0.06
     ire
    -0.06
    Trees
    -0.06
    ует
    -0.06
    POSITIVE LOGITS
    ibrary
    0.07
     Refriger
    0.07
    ESSAGES
    0.06
     conditional
    0.06
     hasil
    0.06
     vým
    0.06
     разви
    0.06
     bitmask
    0.06
    eking
    0.06
    iphy
    0.06
    Act Density 0.008%

    No Known Activations