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

    Neuronpedia

    INDEX
    Explanations

    code commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proprietary
    -0.09
    .pt
    -0.08
     Propriet
    -0.08
     salesman
    -0.07
     khusus
    -0.07
    _sales
    -0.07
    _PUR
    -0.07
     инвест
    -0.07
    public
    -0.07
    -0.07
    POSITIVE LOGITS
     mounts
    0.09
     mount
    0.09
    pital
    0.09
    /world
    0.09
    restrial
    0.09
     �
    0.08
    absolute
    0.08
     Mounted
    0.08
    Absolute
    0.08
     !!!↵
    0.08
    Act Density 0.006%
    No Known Activations