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

    Neuronpedia

    INDEX
    Explanations

    say "vert" or "ceil" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     antique
    -0.07
     ny
    -0.07
    心
    -0.06
    :{}
    -0.06
    .ide
    -0.06
    /location
    -0.06
     speaker
    -0.06
    	vec
    -0.06
    ]int
    -0.06
    ivec
    -0.06
    POSITIVE LOGITS
     multiplayer
    0.07
     everlasting
    0.07
     TimeUnit
    0.06
     carried
    0.06
    .addCell
    0.06
    ecal
    0.06
     grop
    0.06
    ßer
    0.06
     MPC
    0.06
     rooting
    0.06
    Act Density 0.002%

    No Known Activations