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

    Neuronpedia

    INDEX
    Explanations

    Houston

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ynamic
    0.40
     minimum
    0.39
     castell
    0.38
     entusias
    0.38
     bitches
    0.38
     catalogue
    0.37
    十分に
    0.37
    驥
    0.37
    绪
    0.37
     capitalism
    0.36
    POSITIVE LOGITS
    Timber
    0.46
    GetValue
    0.44
    Alfred
    0.42
     Micros
    0.41
     Grover
    0.40
    Ol
    0.39
    SMB
    0.38
     lumber
    0.38
    Lago
    0.38
     Fenton
    0.38
    Act Density 0.002%

    No Known Activations