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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Americ
    -0.07
     Occ
    -0.07
    .lbl
    -0.07
    _b
    -0.07
     Heap
    -0.07
     Toro
    -0.06
     onc
    -0.06
    .@
    -0.06
    _fh
    -0.06
    .Car
    -0.06
    POSITIVE LOGITS
    emap
    0.06
    基础
    0.06
    .lines
    0.06
                        
↵
    0.06
    ASSES
    0.06
     roli
    0.06
    吗
    0.06
     sem
    0.06
    ]=$
    0.06
    0.06
    Act Density 0.253%

    No Known Activations