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

    Neuronpedia

    INDEX
    Explanations

    VPN IP, Junglefowl, SAML library, image generators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Álvaro
    0.43
     Stark
    0.41
     Hend
    0.40
     abord
    0.40
     Miss
    0.39
     този
    0.39
     Detta
    0.39
     Aplikasi
    0.39
     Sandbox
    0.38
     भार
    0.38
    POSITIVE LOGITS
    uchte
    0.41
    oken
    0.40
    orch
    0.39
     ngo
    0.38
    unie
    0.38
    mao
    0.38
    queous
    0.38
    mixture
    0.37
    utsche
    0.37
     humane
    0.37
    Act Density 0.000%

    No Known Activations