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

    Neuronpedia

    INDEX
    Explanations

    small differences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Multip
    -0.07
    -condition
    -0.06
    =\"";↵
    -0.06
     енерг
    -0.06
    воб
    -0.06
    Abs
    -0.06
     selects
    -0.06
     choosing
    -0.06
    gregation
    -0.06
     excited
    -0.06
    POSITIVE LOGITS
    Tools
    0.07
    .findById
    0.06
    .single
    0.06
     registrar
    0.06
     ((_
    0.06
     #@
    0.06
    _host
    0.06
    ́
    0.06
     dept
    0.06
     cpu
    0.06
    Act Density 0.033%

    No Known Activations