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

    Neuronpedia

    INDEX
    Explanations

    improved flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Herstellung
    0.48
     invitations
    0.46
    excluding
    0.44
     tasteless
    0.44
     ionized
    0.44
    fasta
    0.41
     बतौर
    0.41
     ionizing
    0.40
    relli
    0.40
    有害
    0.40
    POSITIVE LOGITS
     nekoliko
    0.44
     aproximativ
    0.44
     semaine
    0.43
     giorno
    0.42
     swojego
    0.42
     aproape
    0.42
     föränd
    0.42
     snowboard
    0.41
     schimb
    0.40
     gjorde
    0.40
    Act Density 0.005%

    No Known Activations