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

    Neuronpedia

    INDEX
    Explanations

    Auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .default
    -0.07
    ######↵
    -0.06
    diler
    -0.06
    所有
    -0.06
    lop
    -0.06
     Assassin
    -0.06
    па
    -0.06
    andaş
    -0.06
     Manager
    -0.06
    	resp
    -0.06
    POSITIVE LOGITS
    echn
    0.07
    video
    0.07
     mal
    0.06
     PIT
    0.06
    arming
    0.06
    drink
    0.06
     MULT
    0.06
     hora
    0.06
    dan
    0.06
    ены
    0.06
    Act Density 0.189%

    No Known Activations