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

    Neuronpedia

    INDEX
    Explanations

    friendships and close relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fragen
    -0.06
     déc
    -0.06
     fø
    -0.06
    .ali
    -0.06
     mia
    -0.06
    (classes
    -0.06
     greedy
    -0.06
     Rams
    -0.06
    <count
    -0.06
    IE
    -0.06
    POSITIVE LOGITS
    weep
    0.07
     unequiv
    0.07
    _VERBOSE
    0.07
    UDIO
    0.07
            	↵
    0.06
     disap
    0.06
     huh
    0.06
    něž
    0.06
    +N
    0.06
    rror
    0.06
    Act Density 0.028%

    No Known Activations