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

    Neuronpedia

    INDEX
    Explanations

    Research papers citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    举é£İ
    -0.28
    è£ħå¤ĩ
    -0.27
    Ľå»º
    -0.25
     osob
    -0.25
     sexually
    -0.25
    å²Ń
    -0.25
    omes
    -0.24
    leccion
    -0.24
    ston
    -0.24
    emi
    -0.24
    POSITIVE LOGITS
    rent
    0.28
    åī¥
    0.28
    bel
    0.27
    :",↵
    0.26
    å¼±
    0.25
    fter
    0.24
    "\↵
    0.24
    çľī
    0.24
    æĭ¿
    0.24
    rub
    0.23
    Act Density 0.020%

    No Known Activations