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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pag
    -0.07
     owing
    -0.07
     combines
    -0.06
    Когда
    -0.06
    dığ
    -0.06
    Double
    -0.06
    ẹp
    -0.06
    ською
    -0.06
    Memory
    -0.06
     Когда
    -0.06
    POSITIVE LOGITS
    .eval
    0.07
     �
    0.07
    =color
    0.06
     prueba
    0.06
     adec
    0.06
     ssl
    0.06
    .tools
    0.06
    ext
    0.06
    .definition
    0.06
    aniel
    0.06
    Act Density 0.048%

    No Known Activations