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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вв
    -0.07
    selectors
    -0.07
    .until
    -0.06
     PASSWORD
    -0.06
     unfortunate
    -0.06
    .Utils
    -0.06
    Unsigned
    -0.06
    .characters
    -0.06
    EK
    -0.06
    	Object
    -0.06
    POSITIVE LOGITS
    你们
    0.07
     Slip
    0.07
    will
    0.07
     nails
    0.07
    opian
    0.07
    *m
    0.07
    onomous
    0.06
    amic
    0.06
     grâce
    0.06
    AMY
    0.06
    Act Density 0.205%

    No Known Activations