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

    Neuronpedia

    INDEX
    Explanations

    instructions and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ko
    0.58
    ky
    0.58
    q
    0.57
    ă
    0.56
    kar
    0.54
    ha
    0.53
    ý
    0.53
    uh
    0.51
    ira
    0.50
    ed
    0.49
    POSITIVE LOGITS
     superson
    0.49
     CIN
    0.48
     według
    0.48
     lanjutan
    0.47
     bantuan
    0.46
    ECON
    0.45
    䐍
    0.45
    LEXPORT
    0.44
     transducers
    0.44
     MATLAB
    0.44
    Act Density 0.001%

    No Known Activations