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

    Neuronpedia

    INDEX
    Explanations

    Amnesia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nullable
    -0.09
     nullable
    -0.09
     regelmatig
    -0.08
     songwriter
    -0.08
     crossings
    -0.08
                            ↵
    -0.08
     flirting
    -0.08
     पालन
    -0.07
    _FLOW
    -0.07
     subcontract
    -0.07
    POSITIVE LOGITS
     scream
    0.11
    ähne
    0.09
     scrambled
    0.08
     bewilder
    0.08
    Perm
    0.08
     noch
    0.08
     sterile
    0.08
     retrouv
    0.08
     survivors
    0.08
     recovered
    0.08
    Act Density 0.045%

    No Known Activations