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

    Neuronpedia

    INDEX
    Explanations

    numbers and identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seals
    -0.07
    絡
    -0.07
     státy
    -0.07
     hanging
    -0.07
    lamp
    -0.06
     headphones
    -0.06
    ơm
    -0.06
     apellido
    -0.06
    FileName
    -0.06
    isphere
    -0.06
    POSITIVE LOGITS
    ρες
    0.07
     heirs
    0.07
     NRL
    0.07
     Ι
    0.06
     Adrian
    0.06
     Міністер
    0.06
     august
    0.06
     те
    0.06
    STRUCTION
    0.06
    anchor
    0.06
    Act Density 0.004%

    No Known Activations