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

    Neuronpedia

    INDEX
    Explanations

    These

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     степени
    -0.08
    .handleClick
    -0.07
     speaker
    -0.07
     tık
    -0.07
    Aug
    -0.07
    िक
    -0.07
     기자
    -0.06
    IK
    -0.06
     kicks
    -0.06
     litres
    -0.06
    POSITIVE LOGITS
     These
    0.10
    These
    0.07
     grate
    0.07
    ethical
    0.07
    wise
    0.07
     eins
    0.07
     idade
    0.06
     dhe
    0.06
    epoch
    0.06
     Blades
    0.06
    Act Density 0.044%

    No Known Activations