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

    Neuronpedia

    INDEX
    Explanations

    code and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    valid
    0.44
    unning
    0.39
     linal
    0.38
    hd
    0.37
    held
    0.37
    pportune
    0.37
    olverine
    0.37
     รอบ
    0.37
    ೮
    0.37
    round
    0.36
    POSITIVE LOGITS
     cab
    0.52
     cabs
    0.50
     ttk
    0.42
    Cab
    0.42
     silber
    0.39
     Cab
    0.39
     nDims
    0.39
     Urinary
    0.39
     code
    0.38
     urinary
    0.38
    Act Density 0.000%

    No Known Activations