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

    Neuronpedia

    INDEX
    Explanations

    strand

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fixed
    -0.07
     kitty
    -0.07
     Jedi
    -0.07
     epoxy
    -0.07
     Kitty
    -0.07
     cambi
    -0.07
     precio
    -0.07
     clinic
    -0.07
    _tid
    -0.07
     liquidity
    -0.06
    POSITIVE LOGITS
     strand
    0.09
     strav
    0.08
    構
    0.08
    [attr
    0.08
    SetBranch
    0.07
    istra
    0.07
     lesbische
    0.07
     strands
    0.07
     SCM
    0.07
     Str
    0.07
    Act Density 0.053%

    No Known Activations