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

    Neuronpedia

    INDEX
    Explanations

    .display in web code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ordo
    0.88
    ϖ
    0.79
     Guildford
    0.76
     Parm
    0.75
     pila
    0.74
    Parm
    0.72
     Parma
    0.72
    PHI
    0.70
    Brit
    0.69
     AX
    0.69
    POSITIVE LOGITS
     Flask
    0.88
     flask
    0.80
    Flask
    0.77
    @
    0.73
     Wallace
    0.72
     @
    0.71
     flash
    0.70
    िकास
    0.69
     Flower
    0.68
     flashes
    0.68
    Act Density 0.108%

    No Known Activations