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

    Neuronpedia

    INDEX
    Explanations

    cancer sounding

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Edmunds
    0.66
     Fill
    0.64
     DOI
    0.63
     Oxygen
    0.58
     bane
    0.57
    FieldName
    0.57
     Ken
    0.57
     drape
    0.57
     Pull
    0.56
     PM
    0.56
    POSITIVE LOGITS
    cis
    0.91
    cic
    0.82
    nagar
    0.82
    cancer
    0.81
    fuzzy
    0.81
     cins
    0.78
    iques
    0.78
    fi
    0.78
    vic
    0.77
    solver
    0.77
    Act Density 0.000%

    No Known Activations