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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     악
    -0.07
     времени
    -0.06
    祝
    -0.06
     blockade
    -0.06
     Lindsay
    -0.06
     Над
    -0.06
     timp
    -0.06
    apr
    -0.06
     води
    -0.06
    Busy
    -0.06
    POSITIVE LOGITS
     dán
    0.07
     pitfalls
    0.07
     жиз
    0.06
     arrow
    0.06
     ($)
    0.06
    'value
    0.06
    :(
    0.06
     abb
    0.06
     advocate
    0.06
     opi
    0.06
    Act Density 0.014%

    No Known Activations