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

    Neuronpedia

    INDEX
    Explanations

    Legal or political text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chern
    -0.07
    Dynamic
    -0.07
    _magic
    -0.07
    directory
    -0.07
    	index
    -0.07
     reacted
    -0.07
    _loading
    -0.06
    字符串
    -0.06
    student
    -0.06
    Factor
    -0.06
    POSITIVE LOGITS
    .her
    0.07
     güzel
    0.06
     pandas
    0.06
    ;if
    0.06
    _UNS
    0.06
     SAF
    0.06
    _RGCTX
    0.06
     antagonist
    0.06
     {*}
    0.06
     erad
    0.06
    Act Density 0.041%

    No Known Activations