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

    Neuronpedia

    INDEX
    Explanations

    come

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    灰
    -0.07
    enden
    -0.07
    <
    -0.07
     observation
    -0.07
     que
    -0.06
    _views
    -0.06
    ="")↵
    -0.06
     validation
    -0.06
    }};↵
    -0.06
     MEMORY
    -0.06
    POSITIVE LOGITS
     Contrib
    0.08
     onPostExecute
    0.07
    ticket
    0.07
     вмест
    0.06
    βι
    0.06
     ارشد
    0.06
     násled
    0.06
    JT
    0.06
     mainAxisAlignment
    0.06
     jose
    0.06
    Act Density 0.009%

    No Known Activations