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

    Neuronpedia

    INDEX
    Explanations

    Slate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bern
    -0.07
     Peterson
    -0.07
     flower
    -0.07
    .providers
    -0.06
    ，把
    -0.06
    剂
    -0.06
     pedals
    -0.06
     explosions
    -0.06
     RG
    -0.06
     urb
    -0.06
    POSITIVE LOGITS
     slate
    0.16
     Slate
    0.15
     slated
    0.10
    Slash
    0.08
    ATE
    0.08
    late
    0.07
     Slack
    0.07
     Skipping
    0.07
     slump
    0.07
    direct
    0.07
    Act Density 0.001%

    No Known Activations