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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abond
    -0.09
     truncated
    -0.08
     apprent
    -0.07
     compréhension
    -0.07
     തൊഴ
    -0.07
     nouveaux
    -0.07
    lesh
    -0.07
     собственной
    -0.07
     œuvre
    -0.07
    _credit
    -0.07
    POSITIVE LOGITS
     rated
    0.08
     synthesis
    0.08
     Linked
    0.08
     specimen
    0.08
     Synth
    0.07
    -rated
    0.07
     Bags
    0.07
     Hemp
    0.07
     alerg
    0.07
     Muster
    0.07
    Act Density 0.005%

    No Known Activations