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

    Neuronpedia

    INDEX
    Explanations

    ps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lim
    -0.07
     LOC
    -0.07
    iam
    -0.07
     LIMITED
    -0.06
    hou
    -0.06
     sibling
    -0.06
    يان
    -0.06
    ############################
    -0.06
     WARN
    -0.06
     Korean
    -0.06
    POSITIVE LOGITS
     ps
    0.28
     Ps
    0.22
    	ps
    0.11
    -ps
    0.10
    Ps
    0.09
    (ps
    0.09
     Psalm
    0.08
     вс
    0.07
    oriasis
    0.07
    ps
    0.06
    Act Density 0.004%

    No Known Activations