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

    Neuronpedia

    INDEX
    Explanations

    have specific expertise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulagway
    0.71
     mencegah
    0.69
     destruir
    0.66
    entropy
    0.66
    waarden
    0.66
     provoque
    0.65
     partícula
    0.65
     불
    0.64
     berubah
    0.64
     순간
    0.63
    POSITIVE LOGITS
     experience
    3.13
     expertise
    3.04
     Experience
    2.67
     familiarity
    2.64
    experience
    2.61
     ervaring
    2.59
     experiencia
    2.59
     experiência
    2.57
    Experience
    2.55
     knowledge
    2.55
    Act Density 0.752%

    No Known Activations