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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HCI
    -0.07
     reminding
    -0.06
     using
    -0.06
     Drawing
    -0.06
     ethics
    -0.06
     submits
    -0.06
    leasing
    -0.06
     onto
    -0.06
     having
    -0.06
     muttered
    -0.06
    POSITIVE LOGITS
     are
    0.10
    ’re
    0.07
     were
    0.07
     Are
    0.07
     повинна
    0.07
     จะ
    0.07
     is
    0.07
    "is
    0.07
    ELY
    0.06
    're
    0.06
    Act Density 0.426%

    No Known Activations