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

    Neuronpedia

    INDEX
    Explanations

    а

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    say
    -0.08
     IPs
    -0.07
    ений
    -0.07
    uede
    -0.07
     fierc
    -0.07
     gun
    -0.07
    fre
    -0.07
     traditions
    -0.07
     Briggs
    -0.06
    udd
    -0.06
    POSITIVE LOGITS
    lasyon
    0.07
     Qual
    0.07
    .published
    0.06
     iar
    0.06
     anale
    0.06
     Dě
    0.06
    .trim
    0.06
     kavram
    0.06
     SERVER
    0.06
    Arrange
    0.06
    Act Density 0.009%

    No Known Activations