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

    Neuronpedia

    INDEX
    Explanations

    ESP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IGN
    -0.07
    991
    -0.07
     перей
    -0.06
     Adding
    -0.06
    /generated
    -0.06
     Pur
    -0.06
    管
    -0.06
    _PCI
    -0.06
     وغير
    -0.06
    /Auth
    -0.06
    POSITIVE LOGITS
     esp
    0.09
     ESP
    0.08
     zejména
    0.07
    .strictEqual
    0.07
     compuls
    0.07
     special
    0.07
    TING
    0.07
    osp
    0.07
    ór
    0.07
     �
    0.07
    Act Density 0.002%

    No Known Activations